no code implementations • EMNLP 2020 • Yijun Wang, Changzhi Sun, Yuanbin Wu, Junchi Yan, Peng Gao, Guotong Xie
In particular, a span encoder is trained to recover a random shuffling of tokens in a span, and a span pair encoder is trained to predict positive pairs that are from the same sentences and negative pairs that are from different sentences using contrastive loss.
no code implementations • ECCV 2020 • Ning Zhang, Junchi Yan
In this work, we propose novel perspectives on the DBD problem and design convenient approach to build a real-time cost-effective DBD model.
no code implementations • ECCV 2020 • Jianchao Zhu, Liangliang Shi, Junchi Yan, Hongyuan Zha
This paper proposes new ways of sample mixing by thinking of the process as generation of barycenter in a metric space for data augmentation.
no code implementations • ECCV 2020 • Jian Hu, Hongya Tuo, Chao Wang, Lingfeng Qiao, Haowen Zhong, Junchi Yan, Zhongliang Jing, Henry Leung
Previous methods typically match the whole source domain to target domain, which causes negative transfer due to the source-negative classes in source domain that does not exist in target domain.
no code implementations • 20 Mar 2024 • Xiaosong Jia, Shaoshuai Shi, Zijun Chen, Li Jiang, Wenlong Liao, Tao He, Junchi Yan
As an essential task in autonomous driving (AD), motion prediction aims to predict the future states of surround objects for navigation.
1 code implementation • 18 Mar 2024 • Beichen Zhang, Xiaoxing Wang, Xiaohan Qin, Junchi Yan
In this work, we analyze the order-preserving ability on the whole search space (global) and a sub-space of top architectures (local), and empirically show that the local order-preserving for current two-stage NAS methods still need to be improved.
no code implementations • 15 Mar 2024 • Han Lu, Yichen Xie, Xiaokang Yang, Junchi Yan
In this paper, we propose a Bi-Level Active Finetuning framework to select the samples for annotation in one shot, which includes two stages: core sample selection for diversity, and boundary sample selection for uncertainty.
no code implementations • 12 Mar 2024 • Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Yu Qiao, Wai Lam, Lizhuang Ma
The rapid advancement of Large Language Models (LLMs) has brought about remarkable capabilities in natural language processing but also raised concerns about their potential misuse.
no code implementations • 5 Mar 2024 • Han Lu, Xiaosong Jia, Yichen Xie, Wenlong Liao, Xiaokang Yang, Junchi Yan
End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm.
no code implementations • 1 Mar 2024 • Han Lu, Siyu Sun, Yichen Xie, Liqing Zhang, Xiaokang Yang, Junchi Yan
In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods.
1 code implementation • 29 Feb 2024 • Zikai Xiao, Guo-Ye Yang, Xue Yang, Tai-Jiang Mu, Junchi Yan, Shi-Min Hu
Considerable efforts have been devoted to Oriented Object Detection (OOD).
1 code implementation • 28 Feb 2024 • Shen Cai, Zhanhao Wu, Lingxi Guo, Jiachun Wang, Siyu Zhang, Junchi Yan, Shuhan Shen
Under the minimal $4$-point configuration, the first and the last similarity transformations in SKS are computed by two anchor points on target and source planes, respectively.
1 code implementation • 27 Feb 2024 • RuiZhe Zhong, Junjie Ye, Zhentao Tang, Shixiong Kai, Mingxuan Yuan, Jianye Hao, Junchi Yan
First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from circuit netlist.
1 code implementation • 22 Feb 2024 • Xudong Lu, Qi Liu, Yuhui Xu, Aojun Zhou, Siyuan Huang, Bo Zhang, Junchi Yan, Hongsheng Li
Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks.
1 code implementation • 19 Feb 2024 • Renqiu Xia, Bo Zhang, Hancheng Ye, Xiangchao Yan, Qi Liu, Hongbin Zhou, Zijun Chen, Min Dou, Botian Shi, Junchi Yan, Yu Qiao
Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously.
1 code implementation • 18 Feb 2024 • Qitian Wu, Fan Nie, Chenxiao Yang, TianYi Bao, Junchi Yan
In this paper, we adopt a bottom-up data-generative perspective and reveal a key observation through causal analysis: the crux of GNNs' failure in OOD generalization lies in the latent confounding bias from the environment.
1 code implementation • 11 Feb 2024 • Fangyu Ding, Haiyang Wang, Zhixuan Chu, Tianming Li, Zhaoping Hu, Junchi Yan
Many recent endeavors of GIL focus on extracting the invariant subgraph from the input graph for prediction as a regularization strategy to improve the generalization performance of graph learning.
no code implementations • 6 Feb 2024 • Zhanpeng Zhou, Zijun Chen, Yilan Chen, Bo Zhang, Junchi Yan
The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning.
no code implementations • 5 Feb 2024 • Xiaoxing Wang, Jiaxing Li, Chao Xue, Wei Liu, Weifeng Liu, Xiaokang Yang, Junchi Yan, DaCheng Tao
BayesianOptimization(BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function through a probabilistic surrogate model, including Tree-structured Parzen Estimator (TPE), random forest (SMAC), and Gaussian process (GP).
no code implementations • 30 Jan 2024 • Danning Lao, Qi Liu, Jiazi Bu, Junchi Yan, Wei Shen
As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount.
1 code implementation • 28 Jan 2024 • Shaofeng Zhang, Jinfa Huang, Qiang Zhou, Zhibin Wang, Fan Wang, Jiebo Luo, Junchi Yan
At inference, we generate images with arbitrary expansion multiples by inputting an anchor image and its corresponding positional embeddings.
no code implementations • 25 Jan 2024 • Zeyu Xi, Ge Shi, Xuefen Li, Junchi Yan, Zun Li, Lifang Wu, Zilin Liu, Liang Wang
We develop a knowledge guided entity-aware video captioning network (KEANet) based on a candidate player list in encoder-decoder form for basketball live text broadcast.
no code implementations • 21 Jan 2024 • Liangliang Shi, Zhaoqi Shen, Junchi Yan
Even with vanilla Softmax trained features, our extensive experimental results show that our method can achieve good results with our improved inference scheme in the testing stage.
no code implementations • 17 Jan 2024 • Nianzu Yang, Kaipeng Zeng, Haotian Lu, Yexin Wu, Zexin Yuan, Shengdian Jiang, Jiaxiang Wu, Yimin Wang, Junchi Yan
Neuronal morphology is essential for studying brain functioning and understanding neurodegenerative disorders.
no code implementations • 11 Jan 2024 • Xijun Li, Fangzhou Zhu, Hui-Ling Zhen, Weilin Luo, Meng Lu, Yimin Huang, Zhenan Fan, Zirui Zhou, Yufei Kuang, Zhihai Wang, Zijie Geng, Yang Li, Haoyang Liu, Zhiwu An, Muming Yang, Jianshu Li, Jie Wang, Junchi Yan, Defeng Sun, Tao Zhong, Yong Zhang, Jia Zeng, Mingxuan Yuan, Jianye Hao, Jun Yao, Kun Mao
To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.
1 code implementation • 28 Dec 2023 • RuiZhe Zhong, Xingbo Du, Shixiong Kai, Zhentao Tang, Siyuan Xu, Hui-Ling Zhen, Jianye Hao, Qiang Xu, Mingxuan Yuan, Junchi Yan
Since circuit can be represented with HDL in a textual format, it is reasonable to question whether LLMs can be leveraged in the EDA field to achieve fully automated chip design and generate circuits with improved power, performance, and area (PPA).
1 code implementation • 26 Dec 2023 • Tianyu Li, Peijin Jia, Bangjun Wang, Li Chen, Kun Jiang, Junchi Yan, Hongyang Li
A map, as crucial information for downstream applications of an autonomous driving system, is usually represented in lanelines or centerlines.
no code implementations • 13 Dec 2023 • Wenjie Wu, Changjun Fan, Jincai Huang, Zhong Liu, Junchi Yan
To the best of our knowledge, this is the first systematic review of ML-related methods for BPP.
2 code implementations • 6 Dec 2023 • Hongyang Li, Yang Li, Huijie Wang, Jia Zeng, Huilin Xu, Pinlong Cai, Li Chen, Junchi Yan, Feng Xu, Lu Xiong, Jingdong Wang, Futang Zhu, Chunjing Xu, Tiancai Wang, Fei Xia, Beipeng Mu, Zhihui Peng, Dahua Lin, Yu Qiao
With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem.
1 code implementation • 4 Dec 2023 • Jinguo Cheng, Ke Li, Yuxuan Liang, Lijun Sun, Junchi Yan, Yuankai Wu
To address this challenge, we present the Super-Multivariate Urban Mobility Transformer (SUMformer), which utilizes a specially designed attention mechanism to calculate temporal and cross-variable correlations and reduce computational costs stemming from a large number of time series.
no code implementations • 27 Nov 2023 • Shaobo Wang, Xiangdong Zhang, Dongrui Liu, Junchi Yan
In this work, we critically examine BN from a feature perspective, identifying feature condensation during BN as a detrimental factor to test performance.
1 code implementation • 23 Nov 2023 • Junwei Luo, Xue Yang, Yi Yu, Qingyun Li, Junchi Yan, Yansheng Li
Single point-supervised object detection is gaining attention due to its cost-effectiveness.
2 code implementations • 23 Nov 2023 • Yi Yu, Xue Yang, Qingyun Li, Feipeng Da, Jifeng Dai, Yu Qiao, Junchi Yan
To our best knowledge, Point2RBox is the first end-to-end solution for point-supervised OOD.
1 code implementation • 14 Nov 2023 • Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan
Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80. 1\%$ to $\mathbf{83. 3\%}$, and BBGM from $79. 0\%$ to $\mathbf{84. 5\%}$.
Ranked #1 on Graph Matching on PASCAL VOC (matching accuracy metric)
no code implementations • 13 Nov 2023 • Haoyu Geng, Hang Ruan, Runzhong Wang, Yang Li, Yang Wang, Lei Chen, Junchi Yan
Numerous web applications rely on solving combinatorial optimization problems, such as energy cost-aware scheduling, budget allocation on web advertising, and graph matching on social networks.
1 code implementation • 8 Nov 2023 • Wujiang Xu, Qitian Wu, Runzhong Wang, Mingming Ha, Qiongxu Ma, Linxun Chen, Bing Han, Junchi Yan
To address these challenges under open-world assumptions, we design an \textbf{A}daptive \textbf{M}ulti-\textbf{I}nterest \textbf{D}ebiasing framework for cross-domain sequential recommendation (\textbf{AMID}), which consists of a multi-interest information module (\textbf{MIM}) and a doubly robust estimator (\textbf{DRE}).
no code implementations • 3 Nov 2023 • Ziyu Wang, Wenhao Jiang, Zixuan Zhang, Wei Tang, Junchi Yan
Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms.
1 code implementation • 2 Nov 2023 • Zhenjie Yang, Xiaosong Jia, Hongyang Li, Junchi Yan
Recently, large language models (LLMs) have demonstrated abilities including understanding context, logical reasoning, and generating answers.
no code implementations • 27 Oct 2023 • Jiaxin Lu, Zetian Jiang, Tianzhe Wang, Junchi Yan
Existing graph matching methods typically assume that there are similar structures between graphs and they are matchable.
no code implementations • 10 Oct 2023 • Ning Liao, Shaofeng Zhang, Renqiu Xia, Min Cao, Yu Qiao, Junchi Yan
Instead of evaluating the models directly, in this paper, we try to evaluate the Vision-Language Instruction-Tuning (VLIT) datasets.
no code implementations • 10 Oct 2023 • Qitian Wu, Chenxiao Yang, Kaipeng Zeng, Fan Nie, Michael Bronstein, Junchi Yan
Graph diffusion equations are intimately related to graph neural networks (GNNs) and have recently attracted attention as a principled framework for analyzing GNN dynamics, formalizing their expressive power, and justifying architectural choices.
no code implementations • 10 Oct 2023 • Yiting Chen, Zhanpeng Zhou, Junchi Yan
In this paper, we expand the concept of equivalent feature and provide the definition of what we call functionally equivalent features.
no code implementations • 8 Oct 2023 • Chenxiao Yang, Qitian Wu, David Wipf, Ruoyu Sun, Junchi Yan
A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner.
1 code implementation • 20 Sep 2023 • Renqiu Xia, Bo Zhang, Haoyang Peng, Hancheng Ye, Xiangchao Yan, Peng Ye, Botian Shi, Yu Qiao, Junchi Yan
Charts are common in literature across different scientific fields, conveying rich information easily accessible to readers.
Ranked #17 on Chart Question Answering on ChartQA (using extra training data)
1 code implementation • 19 Sep 2023 • Xiangchao Yan, Runjian Chen, Bo Zhang, Jiakang Yuan, Xinyu Cai, Botian Shi, Wenqi Shao, Junchi Yan, Ping Luo, Yu Qiao
Our contributions are threefold: (1) Occupancy prediction is shown to be promising for learning general representations, which is demonstrated by extensive experiments on plenty of datasets and tasks.
2 code implementations • 11 Sep 2023 • Bo Zhang, Xinyu Cai, Jiakang Yuan, Donglin Yang, Jianfei Guo, Xiangchao Yan, Renqiu Xia, Botian Shi, Min Dou, Tao Chen, Si Liu, Junchi Yan, Yu Qiao
Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the previous domain knowledge can be hardly directly deployed to a new domain without additional costs.
1 code implementation • ICCV 2023 • Xiaosong Jia, Yulu Gao, Li Chen, Junchi Yan, Patrick Langechuan Liu, Hongyang Li
We find that even equipped with a SOTA perception model, directly letting the student model learn the required inputs of the teacher model leads to poor driving performance, which comes from the large distribution gap between predicted privileged inputs and the ground-truth.
Ranked #2 on CARLA longest6 on CARLA
no code implementations • 23 Jun 2023 • Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan
On classification tasks, for ViT-S, ADCLR achieves 77. 5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0. 5%.
1 code implementation • 20 Jun 2023 • Wentao Zhao, Qitian Wu, Chenxiao Yang, Junchi Yan
Graph structure learning is a well-established problem that aims at optimizing graph structures adaptive to specific graph datasets to help message passing neural networks (i. e., GNNs) to yield effective and robust node embeddings.
1 code implementation • NeurIPS 2023 • Qitian Wu, Wentao Zhao, Chenxiao Yang, Hengrui Zhang, Fan Nie, Haitian Jiang, Yatao Bian, Junchi Yan
Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points.
1 code implementation • 14 Jun 2023 • Qitian Wu, Wentao Zhao, Zenan Li, David Wipf, Junchi Yan
In this paper, we introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes, as an important building block for a pioneering Transformer-style network for node classification on large graphs, dubbed as \textsc{NodeFormer}.
1 code implementation • CVPR 2023 • Xiaosong Jia, Penghao Wu, Li Chen, Jiangwei Xie, Conghui He, Junchi Yan, Hongyang Li
End-to-end autonomous driving has made impressive progress in recent years.
Ranked #4 on CARLA longest6 on CARLA
no code implementations • 7 May 2023 • Yijun Wang, Changzhi Sun, Yuanbin Wu, Lei LI, Junchi Yan, Hao Zhou
Entity relation extraction consists of two sub-tasks: entity recognition and relation extraction.
1 code implementation • NeurIPS 2023 • Huijie Wang, Tianyu Li, Yang Li, Li Chen, Chonghao Sima, Zhenbo Liu, Bangjun Wang, Peijin Jia, Yuting Wang, Shengyin Jiang, Feng Wen, Hang Xu, Ping Luo, Junchi Yan, Wei zhang, Hongyang Li
Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments.
1 code implementation • 11 Apr 2023 • Tianyu Li, Li Chen, Huijie Wang, Yang Li, Jiazhi Yang, Xiangwei Geng, Shengyin Jiang, Yuting Wang, Hang Xu, Chunjing Xu, Junchi Yan, Ping Luo, Hongyang Li
Understanding the road genome is essential to realize autonomous driving.
Ranked #5 on 3D Lane Detection on OpenLane-V2 val
1 code implementation • 6 Apr 2023 • Linyan Huang, Huijie Wang, Jia Zeng, Shengchuan Zhang, Liujuan Cao, Junchi Yan, Hongyang Li
We also conduct experiments on various image backbones and view transformations to validate the efficacy of our approach.
1 code implementation • CVPR 2023 • Yichen Xie, Han Lu, Junchi Yan, Xiaokang Yang, Masayoshi Tomizuka, Wei Zhan
We propose a novel method called ActiveFT for active finetuning task to select a subset of data distributing similarly with the entire unlabeled pool and maintaining enough diversity by optimizing a parametric model in the continuous space.
1 code implementation • 22 Mar 2023 • Chao Chen, Haoyu Geng, Nianzu Yang, Xiaokang Yang, Junchi Yan
Dynamic graphs arise in various real-world applications, and it is often welcomed to model the dynamics directly in continuous time domain for its flexibility.
no code implementations • 9 Mar 2023 • Ning Liao, Bowen Shi, Xiaopeng Zhang, Min Cao, Junchi Yan, Qi Tian
To explore prompt learning on the generative pre-trained visual model, as well as keeping the task consistency, we propose Visual Prompt learning as masked visual Token Modeling (VPTM) to transform the downstream visual classification into the pre-trained masked visual token prediction.
1 code implementation • 9 Mar 2023 • Ying Zeng, Xue Yang, Qingyun Li, Yushi Chen, Junchi Yan
Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model.
no code implementations • 9 Mar 2023 • Ning Liao, Xiaopeng Zhang, Min Cao, Junchi Yan, Qi Tian
In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown classes (i. e., not seen during training), they always predict them as one of the training classes.
1 code implementation • 8 Feb 2023 • Chao Chen, Haoyu Geng, Gang Zeng, Zhaobing Han, Hua Chai, Xiaokang Yang, Junchi Yan
Inductive one-bit matrix completion is motivated by modern applications such as recommender systems, where new users would appear at test stage with the ratings consisting of only ones and no zeros.
1 code implementation • 6 Feb 2023 • Qitian Wu, Yiting Chen, Chenxiao Yang, Junchi Yan
This paves a way for a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 4 Feb 2023 • Yang Li, Xinyan Chen, Wenxuan Guo, Xijun Li, Wanqian Luo, Junhua Huang, Hui-Ling Zhen, Mingxuan Yuan, Junchi Yan
On top of the observations that industrial formulae exhibit clear community structure and oversplit substructures lead to the difficulty in semantic formation of logical structures, we propose HardSATGEN, which introduces a fine-grained control mechanism to the neural split-merge paradigm for SAT formula generation to better recover the structural and computational properties of the industrial benchmarks.
1 code implementation • 23 Jan 2023 • Qitian Wu, Chenxiao Yang, Wentao Zhao, Yixuan He, David Wipf, Junchi Yan
Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired instance representations.
1 code implementation • 3 Jan 2023 • Penghao Wu, Li Chen, Hongyang Li, Xiaosong Jia, Junchi Yan, Yu Qiao
Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving.
1 code implementation • CVPR 2023 • Runzhong Wang, Ziao Guo, Shaofei Jiang, Xiaokang Yang, Junchi Yan
Graph matching (GM) aims at discovering node matching between graphs, by maximizing the node- and edge-wise affinities between the matched elements.
Ranked #1 on Graph Matching on Willow Object Class (F1 score metric)
no code implementations • CVPR 2023 • Jia Zeng, Li Chen, Hanming Deng, Lewei Lu, Junchi Yan, Yu Qiao, Hongyang Li
Specifically, a set of queries are leveraged to locate the instance-level areas for masked feature generation, to intensify feature representation ability in these areas.
1 code implementation • 18 Dec 2022 • Chenxiao Yang, Qitian Wu, Jiahua Wang, Junchi Yan
Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional message passing layers to allow features to flow across nodes.
no code implementations • 8 Dec 2022 • Hengrui Zhang, Qitian Wu, Yu Wang, Shaofeng Zhang, Junchi Yan, Philip S. Yu
Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data.
no code implementations • 3 Dec 2022 • Haoxuan Wang, Junchi Yan
Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters.
Ranked #21 on Long-tail Learning on CIFAR-10-LT (ρ=10)
1 code implementation • NIPS 2022 • Yiting Chen, Qibing Ren, Junchi Yan
In this work, we introduce Shapley value, a metric of cooperative game theory, into the frequency domain and propose to quantify the positive (negative) impact of every frequency component of data on CNNs.
2 code implementations • 24 Oct 2022 • Chenxiao Yang, Qitian Wu, Junchi Yan
We study a new paradigm of knowledge transfer that aims at encoding graph topological information into graph neural networks (GNNs) by distilling knowledge from a teacher GNN model trained on a complete graph to a student GNN model operating on a smaller or sparser graph.
1 code implementation • 24 Oct 2022 • Chenxiao Yang, Qitian Wu, Qingsong Wen, Zhiqiang Zhou, Liang Sun, Junchi Yan
The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment.
no code implementations • 20 Oct 2022 • Min Cao, Cong Ding, Chen Chen, Junchi Yan, Qi Tian
Based on a natural assumption that images belonging to the same person identity should not match with images belonging to multiple different person identities across views, called the unicity of person matching on the identity level, we propose an end-to-end person unicity matching architecture for learning and refining the person matching relations.
no code implementations • 19 Oct 2022 • Zetian Jiang, Jiaxin Lu, Tianzhe Wang, Junchi Yan
We consider the general setting for partial matching of two or multiple graphs, in the sense that not necessarily all the nodes in one graph can find their correspondences in another graph and vice versa.
2 code implementations • 13 Oct 2022 • Xue Yang, Gefan Zhang, Wentong Li, Xuehui Wang, Yue Zhou, Junchi Yan
Oriented object detection emerges in many applications from aerial images to autonomous driving, while many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated box, leading to a gap between the readily available training corpus and the rising demand for oriented object detection.
1 code implementation • 22 Sep 2022 • Xue Yang, Gefan Zhang, Xiaojiang Yang, Yue Zhou, Wentao Wang, Jin Tang, Tao He, Junchi Yan
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects.
1 code implementation • 15 Jul 2022 • Shengchao Hu, Li Chen, Penghao Wu, Hongyang Li, Junchi Yan, DaCheng Tao
In particular, we propose a spatial-temporal feature learning scheme towards a set of more representative features for perception, prediction and planning tasks simultaneously, which is called ST-P3.
Ranked #7 on Bird's-Eye View Semantic Segmentation on nuScenes (IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 metric)
1 code implementation • 16 Jun 2022 • Penghao Wu, Xiaosong Jia, Li Chen, Junchi Yan, Hongyang Li, Yu Qiao
The two branches are connected so that the control branch receives corresponding guidance from the trajectory branch at each time step.
Ranked #3 on Autonomous Driving on CARLA Leaderboard
no code implementations • 16 Jun 2022 • Li Chen, Tutian Tang, Zhitian Cai, Yang Li, Penghao Wu, Hongyang Li, Jianping Shi, Junchi Yan, Yu Qiao
Equipped with a wide span of sensors, predominant autonomous driving solutions are becoming more modular-oriented for safe system design.
1 code implementation • 2 Jun 2022 • Jian Hu, Haowen Zhong, Junchi Yan, Shaogang Gong, Guile Wu, Fei Yang
However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i. e., biased domain adaptation.
no code implementations • 21 May 2022 • Xuhong Wang, Sirui Chen, Yixuan He, Minjie Wang, Quan Gan, Yupu Yang, Junchi Yan
Many real world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represented as an edge along with its occurrence timestamp in the graphs. However, most previous works approach the problem in compromised settings, either formulating it as a link prediction task on the graph given the event time or a time prediction problem given which event will happen next.
1 code implementation • 30 Apr 2022 • Xiaosong Jia, Penghao Wu, Li Chen, Yu Liu, Hongyang Li, Junchi Yan
Based on these observations, we propose Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges.
no code implementations • 28 Apr 2022 • Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang
Scalability is an important consideration for deep graph neural networks.
1 code implementation • 28 Apr 2022 • Yue Zhou, Xue Yang, Gefan Zhang, Jiabao Wang, Yanyi Liu, Liping Hou, Xue Jiang, Xingzhao Liu, Junchi Yan, Chengqi Lyu, Wenwei Zhang, Kai Chen
We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning.
1 code implementation • 18 Apr 2022 • Wujiang Xu, Runzhong Wang, Xiaobo Guo, Shaoshuai Li, Qiongxu Ma, Yunan Zhao, Sheng Guo, Zhenfeng Zhu, Junchi Yan
However, the optimal video summaries need to reflect the most valuable keyframe with its own information, and one with semantic power of the whole content.
1 code implementation • IEEE Transactions on Knowledge and Data Engineering 2021 • Chao Chen, Dongsheng Li, Junchi Yan, Xiaokang Yang
Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time.
1 code implementation • 30 Mar 2022 • Chao Chen, Haoyu Geng, Nianzu Yang, Junchi Yan, Daiyue Xue, Jianping Yu, Xiaokang Yang
User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data.
no code implementations • 24 Mar 2022 • Jiawei Sun, Ruoxin Chen, Jie Li, Chentao Wu, Yue Ding, Junchi Yan
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations.
2 code implementations • 21 Mar 2022 • Li Chen, Chonghao Sima, Yang Li, Zehan Zheng, Jiajie Xu, Xiangwei Geng, Hongyang Li, Conghui He, Jianping Shi, Yu Qiao, Junchi Yan
Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.).
Ranked #5 on 3D Lane Detection on Apollo Synthetic 3D Lane
no code implementations • 21 Mar 2022 • Xiaoxing Wang, Jiale Lin, Junchi Yan, Juanping Zhao, Xiaokang Yang
In contrast, this paper introduces an efficient framework, named EAutoDet, that can discover practical backbone and FPN architectures for object detection in 1. 4 GPU-days.
Ranked #30 on Object Detection In Aerial Images on DOTA (using extra training data)
2 code implementations • CVPR 2022 • Xuehui Yu, Pengfei Chen, Di wu, Najmul Hassan, Guorong Li, Junchi Yan, Humphrey Shi, Qixiang Ye, Zhenjun Han
In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
no code implementations • 6 Mar 2022 • Jiayi Zhang, Chang Liu, Junchi Yan, Xijun Li, Hui-Ling Zhen, Mingxuan Yuan
This paper surveys the trend of leveraging machine learning to solve mixed integer programming (MIP) problems.
no code implementations • 2 Mar 2022 • Wenxuan Guo, Junchi Yan, Hui-Ling Zhen, Xijun Li, Mingxuan Yuan, Yaohui Jin
This paper reviews the recent literature on solving the Boolean satisfiability problem (SAT), an archetypal NP-complete problem, with the help of machine learning techniques.
no code implementations • 28 Feb 2022 • Junchi Yan, Xianglong Lyu, Ruoyu Cheng, Yibo Lin
Placement and routing are two indispensable and challenging (NP-hard) tasks in modern chip design flows.
1 code implementation • 28 Feb 2022 • Zhijie Chen, Mingquan Feng, Junchi Yan, Hongyuan Zha
The past few years have witnessed an increased interest in learning Hamiltonian dynamics in deep learning frameworks.
no code implementations • 19 Feb 2022 • Yehui Tang, Junchi Yan, Hancock Edwin
Quantum computing (QC) is a new computational paradigm whose foundations relate to quantum physics.
no code implementations • 18 Feb 2022 • Nianzu Yang, Huaijin Wu, Kaipeng Zeng, Yang Li, Junchi Yan
Machine learning, particularly graph learning, is gaining increasing recognition for its transformative impact across various fields.
10 code implementations • 15 Feb 2022 • Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, Liang Sun
From the perspective of network structure, we summarize the adaptations and modifications that have been made to Transformers in order to accommodate the challenges in time series analysis.
2 code implementations • ICLR 2022 • Qitian Wu, Hengrui Zhang, Junchi Yan, David Wipf
There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight.
1 code implementation • 1 Feb 2022 • Yixuan He, Quan Gan, David Wipf, Gesine Reinert, Junchi Yan, Mihai Cucuringu
In this paper, we introduce neural networks into the ranking recovery problem by proposing the so-called GNNRank, a trainable GNN-based framework with digraph embedding.
3 code implementations • 29 Jan 2022 • Xue Yang, Yue Zhou, Gefan Zhang, Jirui Yang, Wentao Wang, Junchi Yan, Xiaopeng Zhang, Qi Tian
This is in contrast to recent Gaussian modeling based rotation detectors e. g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors.
no code implementations • 13 Jan 2022 • Xing Ai, Zhihong Zhang, Luzhe Sun, Junchi Yan, Edwin Hancock
The architecture is based on a novel mapping from real-world data to Hilbert space.
1 code implementation • CVPR 2022 • Qibing Ren, Qingquan Bao, Runzhong Wang, Junchi Yan
We first show that an adversarial attack on keypoint localities and the hidden graphs can cause significant accuracy drop to deep GM models.
Ranked #6 on Graph Matching on PASCAL VOC (matching accuracy metric)
no code implementations • CVPR 2022 • Shaofeng Zhang, Lyn Qiu, Feng Zhu, Junchi Yan, Hengrui Zhang, Rui Zhao, Hongyang Li, Xiaokang Yang
Existing symmetric contrastive learning methods suffer from collapses (complete and dimensional) or quadratic complexity of objectives.
1 code implementation • CVPR 2022 • Lei Liu, Yuze Chen, Junchi Yan, Yinqiang Zheng
The industry practice for night video surveillance is to use auxiliary near-infrared (NIR) LED diodes, usually centered at 850nm or 940nm, for scene illumination.
no code implementations • 28 Dec 2021 • Han Lu, Zenan Li, Runzhong Wang, Qibing Ren, Junchi Yan, Xiaokang Yang
Solving combinatorial optimization (CO) on graphs is among the fundamental tasks for upper-stream applications in data mining, machine learning and operations research.
no code implementations • NeurIPS 2021 • Longyuan Li, Jian Yao, Li Wenliang, Tong He, Tianjun Xiao, Junchi Yan, David Wipf, Zheng Zhang
Learning the distribution of future trajectories conditioned on the past is a crucial problem for understanding multi-agent systems.
1 code implementation • 12 Nov 2021 • Xue Yang, Yue Zhou, Junchi Yan
AlphaRotate is an open-source Tensorflow benchmark for performing scalable rotation detection on various datasets.
2 code implementations • NeurIPS 2021 • Ruoyu Cheng, Junchi Yan
To achieve end-to-end placement learning, we first propose a joint learning method termed by DeepPlace for the placement of macros and standard cells, by the integration of reinforcement learning with a gradient based optimization scheme.
no code implementations • 10 Oct 2021 • Xiaoxing Wang, Wenxuan Guo, Junchi Yan, Jianlin Su, Xiaokang Yang
Also, we search on the search space of DARTS to compare with peer methods, and our discovered architecture achieves 97. 54% accuracy on CIFAR-10 and 75. 7% top-1 accuracy on ImageNet, which are state-of-the-art performance.
1 code implementation • NeurIPS 2021 • Qitian Wu, Chenxiao Yang, Junchi Yan
We target open-world feature extrapolation problem where the feature space of input data goes through expansion and a model trained on partially observed features needs to handle new features in test data without further retraining.
no code implementations • 30 Sep 2021 • Xiaoxing Wang, Xiangxiang Chu, Junchi Yan, Xiaokang Yang
Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures.
no code implementations • 29 Sep 2021 • Runzhong Wang, Li Shen, Yiting Chen, Junchi Yan, Xiaokang Yang, DaCheng Tao
Cardinality constrained combinatorial optimization requires selecting an optimal subset of $k$ elements, and it will be appealing to design data-driven algorithms that perform TopK selection over a probability distribution predicted by a neural network.
no code implementations • ICLR 2022 • Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang
The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.
no code implementations • ICLR 2022 • Shuang Li, Mingquan Feng, Lu Wang, Abdelmajid Essofi, Yufeng Cao, Junchi Yan, Le Song
We propose a principled method to learn a set of human-readable logic rules to explain temporal point processes.
no code implementations • 29 Sep 2021 • Hengrui Zhang, Qitian Wu, Shaofeng Zhang, Junchi Yan, David Wipf, Philip S. Yu
In this paper, we propose ESCo (Effective and Scalable Contrastive), a new contrastive framework which is essentially an instantiation of the Information Bottleneck principle under self-supervised learning settings.
no code implementations • 29 Sep 2021 • Yunhao Zhang, Junchi Yan, Zhenyu Ren, Jian Yin
To fill the gap, we propose Mixture of Neural Temporal Point Processes (NTPP-MIX), a general framework that can utilize many existing NTPPs for event sequence clustering.
no code implementations • 29 Sep 2021 • Liangliang Shi, Fangyu Ding, Junchi Yan, Yanjie Duan, Guangjian Tian
Despite the fast advance in neural temporal point processes (NTPP) which enjoys high model capacity, there are still some standing gaps to fill including model expressiveness, predictability, and interpretability, especially with the wide application of event sequence modeling.
no code implementations • 29 Sep 2021 • Shaofeng Zhang, Meng Liu, Junchi Yan, Hengrui Zhang, Lingxiao Huang, Pinyan Lu, Xiaokang Yang
Negative pairs are essential in contrastive learning, which plays the role of avoiding degenerate solutions.
no code implementations • 29 Sep 2021 • Qibing Ren, Liangliang Shi, Lanjun Wang, Junchi Yan
We first show both theoretically and empirically that strong smoothing in AT increases local smoothness of the loss surface which is beneficial for robustness but sacrifices the training loss which influences the accuracy of samples near the decision boundary.
no code implementations • 29 Sep 2021 • Yang Li, Yichuan Mo, Liangliang Shi, Junchi Yan, Xiaolu Zhang, Jun Zhou
Although many efforts have been made in terms of backbone architecture design, loss function, and training techniques, few results have been obtained on how the sampling in latent space can affect the final performance, and existing works on latent space mainly focus on controllability.
no code implementations • ICLR 2022 • Xiaojiang Yang, Yi Wang, Jiacheng Sun, Xing Zhang, Shifeng Zhang, Zhenguo Li, Junchi Yan
Nonlinear ICA is a fundamental problem in machine learning, aiming to identify the underlying independent components (sources) from data which is assumed to be a nonlinear function (mixing function) of these sources.
1 code implementation • 24 Sep 2021 • Zeyuan Chen, Wei zhang, Junchi Yan, Gang Wang, Jianyong Wang
Sequential Recommendation aims to recommend items that a target user will interact with in the near future based on the historically interacted items.
1 code implementation • 24 Sep 2021 • Wen Qian, Xue Yang, Silong Peng, Junchi Yan, Xiujuan Zhang
We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration.
no code implementations • 9 Sep 2021 • Qiang Zhang, Yunzhu Li, Yiyue Luo, Wan Shou, Michael Foshey, Junchi Yan, Joshua B. Tenenbaum, Wojciech Matusik, Antonio Torralba
This work takes a step on dynamics modeling in hand-object interactions from dense tactile sensing, which opens the door for future applications in activity learning, human-computer interactions, and imitation learning for robotics.
no code implementations • 20 Jul 2021 • Yuanzhou Chen, Shaobo Cai, Yuxin Wang, Junchi Yan
We propose a monocular vision technology based ELC method.
1 code implementation • ACL 2021 • Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei LI, Junchi Yan
Entities and relations are represented by squares and rectangles in the table.
1 code implementation • NeurIPS 2021 • Hengrui Zhang, Qitian Wu, Junchi Yan, David Wipf, Philip S. Yu
We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data.
1 code implementation • CVPR 2021 • Xu Yang, Cheng Deng, Zhiyuan Dang, Kun Wei, Junchi Yan
Specifically, the Identity Aggregation is applied to extract semantic features from labeled nodes, the Semantic Alignment is utilized to align node features obtained from different aspects using the class central similarity.
1 code implementation • NeurIPS 2021 • Runzhong Wang, Zhigang Hua, Gan Liu, Jiayi Zhang, Junchi Yan, Feng Qi, Shuang Yang, Jun Zhou, Xiaokang Yang
Combinatorial Optimization (CO) has been a long-standing challenging research topic featured by its NP-hard nature.
2 code implementations • NeurIPS 2021 • Xue Yang, Xiaojiang Yang, Jirui Yang, Qi Ming, Wentao Wang, Qi Tian, Junchi Yan
Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection.
Ranked #14 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • 1 Jun 2021 • Yang Li, Liangliang Shi, Junchi Yan
Based on this observation, considering a necessary condition of IID generation that the inverse samples from target data should also be IID in the source distribution, we propose a new loss to encourage the closeness between inverse samples of real data and the Gaussian source in latent space to regularize the generation to be IID from the target distribution.
1 code implementation • AAAI 2021 • Chao Chen, Dongsheng Li, Junchi Yan, Hanchi Huang, Xiaokang Yang
One-bit matrix completion is an important class of positiveunlabeled (PU) learning problems where the observations consist of only positive examples, eg, in top-N recommender systems.
1 code implementation • EACL 2021 • Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei LI, Junchi Yan
Current state-of-the-art systems for joint entity relation extraction (Luan et al., 2019; Wad-den et al., 2019) usually adopt the multi-task learning framework.
no code implementations • CVPR 2021 • Bo Sun, Junchi Yan, Xiao Zhou, Yinqiang Zheng
To reconstruct spectral signals from multi-channel observations, in particular trichromatic RGBs, has recently emerged as a promising alternative to traditional scanning-based spectral imager.
no code implementations • CVPR 2021 • Yuchen Luo, Yong Zhang, Junchi Yan, Wei Liu
The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective.
no code implementations • 23 Mar 2021 • Mingyu Wu, Boyuan Jiang, Donghao Luo, Junchi Yan, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Xiaokang Yang
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame.
no code implementations • 2 Feb 2021 • Longyuan Li, Junchi Yan, Haiyang Wang, Yaohui Jin
Our model is based on Variational Auto-Encoder (VAE), and its backbone is fulfilled by a Recurrent Neural Network to capture latent temporal structures of time series for both generative model and inference model.
no code implementations • 31 Jan 2021 • Longyuan Li, Jihai Zhang, Junchi Yan, Yaohui Jin, Yunhao Zhang, Yanjie Duan, Guangjian Tian
Time-series is ubiquitous across applications, such as transportation, finance and healthcare.
no code implementations • 31 Jan 2021 • Longyuan Li, Junchi Yan, Xiaokang Yang, Yaohui Jin
We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks and the dependency is modeled by recurrent neural nets.
2 code implementations • 28 Jan 2021 • Xue Yang, Junchi Yan, Qi Ming, Wentao Wang, Xiaopeng Zhang, Qi Tian
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.
Ranked #16 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • 11 Jan 2021 • Yuanyuan Ding, Junchi Yan, Guoqiang Hu, Jun Zhu
This paper discloses a novel visual inspection system for liquid crystal display (LCD), which is currently a dominant type in the FPD industry.
no code implementations • 1 Jan 2021 • Shaofeng Zhang, Junchi Yan, Xiaokang Yang
Despite their success in perception over the last decade, deep neural networks are also known ravenous to labeled data for training, which limits their applicability to real-world problems.
no code implementations • 1 Jan 2021 • Liangliang Shi, Yang Li, Junchi Yan
Generative adversarial networks have shown their ability in capturing high-dimensional complex distributions and generating realistic data samples e. g. images.
no code implementations • 1 Jan 2021 • Xiaojiang Yang, Yitong Sun, Junchi Yan
In our experiments, we find that even the data is only augmented along a few latent variables, more latent variables can be identified, and adding a small noise in data space can stabilize this outcome.
no code implementations • 1 Jan 2021 • Haoran Liao, Junchi Yan, Zimin Feng
Bayesian optimization, whose efficiency for automatic hyperparameter tuning has been verified over the decade, still faces a standing dilemma between massive consumption of time and suboptimal search results.
no code implementations • 1 Jan 2021 • Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li
Graph matching (GM) has been traditionally modeled as a deterministic optimization problem characterized by an affinity matrix under pre-defined graph topology.
2 code implementations • 16 Dec 2020 • Chang Liu, Zetian Jiang, Runzhong Wang, Junchi Yan, Lingxiao Huang, Pinyan Lu
As such, the agent can finish inlier matching timely when the affinity score stops growing, for which otherwise an additional parameter i. e. the number of inliers is needed to avoid matching outliers.
1 code implementation • NeurIPS 2020 • Xu Yang, Cheng Deng, Kun Wei, Junchi Yan, Wei Liu
Meanwhile, we devise an adversarial attack strategy to explore samples that easily fool the clustering layers but do not impact the performance of the deep embedding.
no code implementations • NeurIPS 2020 • Shaofeng Zhang, Meng Liu, Junchi Yan
Ensemble is a general way of improving the accuracy and stability of learning models, especially for the generalization ability on small datasets.
1 code implementation • NeurIPS 2020 • Runzhong Wang, Junchi Yan, Xiaokang Yang
This paper considers the setting of jointly matching and clustering multiple graphs belonging to different groups, which naturally rises in many realistic problems.
Ranked #2 on Graph Matching on Willow Object Class
no code implementations • CVPR 2021 • Runzhong Wang, Tianqi Zhang, Tianshu Yu, Junchi Yan, Xiaokang Yang
This paper presents a hybrid approach by combing the interpretability of traditional search-based techniques for producing the edit path, as well as the efficiency and adaptivity of deep embedding models to achieve a cost-effective GED solver.
no code implementations • ICCV 2023 • Xiaoxing Wang, Xiangxiang Chu, Yuda Fan, Zhexi Zhang, Bo Zhang, Xiaokang Yang, Junchi Yan
Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory.
3 code implementations • CVPR 2021 • Xue Yang, Liping Hou, Yue Zhou, Wentao Wang, Junchi Yan
Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc.
Ranked #29 on Object Detection In Aerial Images on DOTA (using extra training data)
1 code implementation • 13 Nov 2020 • Xuehui Wang, Qing Wang, Yuzhi Zhao, Junchi Yan, Lei Fan, Long Chen
In this paper, we develop a computation efficient yet accurate network based on the proposed attentive auxiliary features (A$^2$F) for SISR.
no code implementations • 8 Oct 2020 • Haoxuan Wang, Zhiding Yu, Yisong Yue, Anima Anandkumar, Anqi Liu, Junchi Yan
We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution.
1 code implementation • ICLR 2021 • Xiangxiang Chu, Xiaoxing Wang, Bo Zhang, Shun Lu, Xiaolin Wei, Junchi Yan
We call this approach DARTS-.
Ranked #19 on Neural Architecture Search on NAS-Bench-201, CIFAR-10
no code implementations • 13 Jul 2020 • Lifang Wu, Zhou Yang, Qi. Wang, Meng Jian, Boxuan Zhao, Junchi Yan, Chang Wen Chen
Based on the observations, we propose a scheme to fuse global and local motion patterns (MPs) and key visual information (KVI) for semantic event recognition in basketball videos.
1 code implementation • 9 Jul 2020 • Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Junchi Yan, Hongyuan Zha
The first model follows conventional matrix factorization which factorizes a group of key users' rating matrix to obtain meta latents.
1 code implementation • 27 May 2020 • Zhongpai Gao, Guangtao Zhai, Junchi Yan, Xiaokang Yang
Various point neural networks have been developed with isotropic filters or using weighting matrices to overcome the structure inconsistency on point clouds.
5 code implementations • 28 Apr 2020 • Xue Yang, Junchi Yan, Wenlong Liao, Xiaokang Yang, Jin Tang, Tao He
Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects.
Ranked #33 on Object Detection In Aerial Images on DOTA (using extra training data)
1 code implementation • 21 Apr 2020 • Zhongpai Gao, Junchi Yan, Guangtao Zhai, Juyong Zhang, Yiyan Yang, Xiaokang Yang
Mesh is a powerful data structure for 3D shapes.
no code implementations • 17 Apr 2020 • Wenhao Li, Bo Jin, Xiangfeng Wang, Junchi Yan, Hongyuan Zha
Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications, due to non-interactivity between agents, curse of dimensionality and computation complexity.
Multi-agent Reinforcement Learning Reinforcement Learning (RL) +2
1 code implementation • 17 Mar 2020 • Yiren Li, Zheng Huang, Junchi Yan, Yi Zhou, Fan Ye, Xianhui Liu
Tabular data is a crucial form of information expression, which can organize data in a standard structure for easy information retrieval and comparison.
4 code implementations • ECCV 2020 • Xue Yang, Junchi Yan
For the resulting circularly distributed angle classification problem, we first devise a Circular Smooth Label technique to handle the periodicity of angle and increase the error tolerance to adjacent angles.
Ranked #37 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • 11 Feb 2020 • Junjie Sheng, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenhao Li, Tsung-Hui Chang, Jun Wang, Hongyuan Zha
This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 11 Feb 2020 • Yun Hua, Xiangfeng Wang, Bo Jin, Wenhao Li, Junchi Yan, Xiaofeng He, Hongyuan Zha
In spite of the success of existing meta reinforcement learning methods, they still have difficulty in learning a meta policy effectively for RL problems with sparse reward.
no code implementations • ICLR 2020 • Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li
Graph matching aims to establishing node-wise correspondence between two graphs, which is a classic combinatorial problem and in general NP-complete.
Ranked #15 on Graph Matching on PASCAL VOC (matching accuracy metric)
1 code implementation • 26 Nov 2019 • Runzhong Wang, Junchi Yan, Xiaokang Yang
We also show how to extend our network to hypergraph matching, and matching of multiple graphs.
Ranked #6 on Graph Matching on SPair-71k
no code implementations • 25 Nov 2019 • Xiaojiang Yang, Wendong Bi, Yitong Sun, Yu Cheng, Junchi Yan
Most existing works on disentangled representation learning are solely built upon an marginal independence assumption: all factors in disentangled representations should be statistically independent.
no code implementations • 21 Nov 2019 • Zhijie Chen, Junchi Yan, Longyuan Li, Xiaokang Yang
Our model is aimed to reconstruct neuron information while inferring representations of neuron spiking states.
no code implementations • 20 Nov 2019 • Jun-Jie Wang, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenjie Zhang, Hongyuan Zha
To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural network.
2 code implementations • 19 Nov 2019 • Wen Qian, Xue Yang, Silong Peng, Yue Guo, Junchi Yan
Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function.
Ranked #43 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • WS 2019 • Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, Guotong Xie
We have experimented both (a) improving the fine-tuning of pre-trained language models on a task with a small dataset size, by leveraging datasets of similar tasks; and (b) incorporating the distributional representations of a KG onto the representations of pre-trained language models, via simply concatenation or multi-head attention.
Ranked #17 on Common Sense Reasoning on ReCoRD
1 code implementation • NeurIPS 2019 • Qitian Wu, Zixuan Zhang, Xiaofeng Gao, Junchi Yan, Guihai Chen
We target modeling latent dynamics in high-dimension marked event sequences without any prior knowledge about marker relations.
10 code implementations • 15 Aug 2019 • Xue Yang, Junchi Yan, Ziming Feng, Tao He
Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features.
no code implementations • 29 May 2019 • Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha
Temporal point process is an expressive tool for modeling event sequences over time.
no code implementations • CVPR 2019 • Xu Yang, Cheng Deng, Feng Zheng, Junchi Yan, Wei Liu
In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering.
1 code implementation • ICCV 2019 • Runzhong Wang, Junchi Yan, Xiaokang Yang
In addition with its NP-completeness nature, another important challenge is effective modeling of the node-wise and structure-wise affinity across graphs and the resulting objective, to guide the matching procedure effectively finding the true matching against noises.
no code implementations • NeurIPS 2018 • Tianshu Yu, Junchi Yan, Yilin Wang, Wei Liu, Baoxin Li
Graph matching has received persistent attention over decades, which can be formulated as a quadratic assignment problem (QAP).
3 code implementations • ICCV 2019 • Xue Yang, Jirui Yang, Junchi Yan, Yue Zhang, Tengfei Zhang, Zhi Guo, Sun Xian, Kun fu
Specifically, a sampling fusion network is devised which fuses multi-layer feature with effective anchor sampling, to improve the sensitivity to small objects.
Ranked #47 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • 6 Nov 2018 • Dongsheng Li, Chao Chen, Qin Lv, Junchi Yan, Li Shang, Stephen M. Chu
Collaborative filtering (CF) is a popular technique in today's recommender systems, and matrix approximation-based CF methods have achieved great success in both rating prediction and top-N recommendation tasks.
no code implementations • ECCV 2018 • Tianshu Yu, Junchi Yan, Wei Liu, Baoxin Li
In this paper, we present an incremental multi-graph matching approach, which deals with the arriving graph utilizing the previous matching results under the global consistency constraint.
no code implementations • 21 Jan 2018 • Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha
In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i. e. a marker.
no code implementations • 15 Jan 2018 • Ao Zhang, Nan Li, Jian Pu, Jun Wang, Junchi Yan, Hongyuan Zha
Learning a classifier with control on the false-positive rate plays a critical role in many machine learning applications.
no code implementations • 6 Dec 2017 • Xiaoyong Pan, Junchi Yan
In this study, we present an attention based convolutional neural network, iDeepA, to predict RNA-protein binding sites from raw RNA sequences.
no code implementations • CVPR 2018 • Tianshu Yu, Junchi Yan, Jieyi Zhao, Baoxin Li
As two fundamental problems, graph cuts and graph matching have been investigated over decades, resulting in vast literature in these two topics respectively.
no code implementations • ACL 2017 • Chengyu Wang, Junchi Yan, Aoying Zhou, Xiaofeng He
Finding the correct hypernyms for entities is essential for taxonomy learning, fine-grained entity categorization, query understanding, etc.
2 code implementations • 24 May 2017 • Shuai Xiao, Junchi Yan, Stephen M. Chu, Xiaokang Yang, Hongyuan Zha
In this paper, we model the background by a Recurrent Neural Network (RNN) with its units aligned with time series indexes while the history effect is modeled by another RNN whose units are aligned with asynchronous events to capture the long-range dynamics.
1 code implementation • NeurIPS 2017 • Shuai Xiao, Mehrdad Farajtabar, Xiaojing Ye, Junchi Yan, Le Song, Hongyuan Zha
Point processes are becoming very popular in modeling asynchronous sequential data due to their sound mathematical foundation and strength in modeling a variety of real-world phenomena.
1 code implementation • 12 Apr 2017 • Wenjie Zhang, Junchi Yan, Xiangfeng Wang, Hongyuan Zha
Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data.
no code implementations • 24 Mar 2017 • Shuai Xiao, Junchi Yan, Mehrdad Farajtabar, Le Song, Xiaokang Yang, Hongyuan Zha
A variety of real-world processes (over networks) produce sequences of data whose complex temporal dynamics need to be studied.
no code implementations • 20 Mar 2017 • Weiyao Lin, Yang shen, Junchi Yan, Mingliang Xu, Jianxin Wu, Jingdong Wang, Ke Lu
We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair.
no code implementations • 21 Feb 2017 • Jinfeng Yi, Qi Lei, Wesley Gifford, Ji Liu, Junchi Yan
In order to efficiently solve the proposed framework, we propose a parameter-free and scalable optimization algorithm by effectively exploring the sparse and low-rank structure of the tensor.
no code implementations • 10 Sep 2016 • Weiyao Lin, Yang Zhou, Hongteng Xu, Junchi Yan, Mingliang Xu, Jianxin Wu, Zicheng Liu
Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a context-rich way to describe the global motion pattern in a scene.
no code implementations • 12 Jun 2016 • Junchi Yan, Zhe Ren, Hongyuan Zha, Stephen Chu
In this paper, we consider the problem of finding the feature correspondences among a collection of feature sets, by using their point-wise unary features.
5 code implementations • 16 May 2016 • Fengfu Li, Bin Liu, Xiaoxing Wang, Bo Zhang, Junchi Yan
We present a memory and computation efficient ternary weight networks (TWNs) - with weights constrained to +1, 0 and -1.
no code implementations • 6 Apr 2016 • Changsheng Li, Junchi Yan, Fan Wei, Weishan Dong, Qingshan Liu, Hongyuan Zha
In this paper, we propose a novel multi-task learning (MTL) framework, called Self-Paced Multi-Task Learning (SPMTL).