Search Results for author: Zhengping Che

Found 34 papers, 6 papers with code

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

no code implementations31 Jan 2024 Dong Chen, Ning Liu, Yichen Zhu, Zhengping Che, Rui Ma, Fachao Zhang, Xiaofeng Mou, Yi Chang, Jian Tang

Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network.

Knowledge Distillation Network Pruning +1

SWBT: Similarity Weighted Behavior Transformer with the Imperfect Demonstration for Robotic Manipulation

no code implementations17 Jan 2024 Kun Wu, Ning Liu, Zhen Zhao, Di Qiu, Jinming Li, Zhengping Che, Zhiyuan Xu, Qinru Qiu, Jian Tang

Imitation learning (IL), aiming to learn optimal control policies from expert demonstrations, has been an effective method for robot manipulation tasks.

Imitation Learning Robot Manipulation

SM$^3$: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects

no code implementations17 Jan 2024 Haowen Wang, Zhen Zhao, Zhao Jin, Zhengping Che, Liang Qiao, Yakun Huang, Zhipeng Fan, XIUQUAN QIAO, Jian Tang

Reconstructing real-world objects and estimating their movable joint structures are pivotal technologies within the field of robotics.

An Efficient Generalizable Framework for Visuomotor Policies via Control-aware Augmentation and Privilege-guided Distillation

no code implementations17 Jan 2024 Yinuo Zhao, Kun Wu, Tianjiao Yi, Zhiyuan Xu, Xiaozhu Ju, Zhengping Che, Qinru Qiu, Chi Harold Liu, Jian Tang

Visuomotor policies, which learn control mechanisms directly from high-dimensional visual observations, confront challenges in adapting to new environments with intricate visual variations.

Data Augmentation Reinforcement Learning (RL) +1

Language-Conditioned Robotic Manipulation with Fast and Slow Thinking

no code implementations8 Jan 2024 Minjie Zhu, Yichen Zhu, Jinming Li, Junjie Wen, Zhiyuan Xu, Zhengping Che, Chaomin Shen, Yaxin Peng, Dong Liu, Feifei Feng, Jian Tang

The language-conditioned robotic manipulation aims to transfer natural language instructions into executable actions, from simple pick-and-place to tasks requiring intent recognition and visual reasoning.

Decision Making Intent Recognition +2

Cross-Modal Reasoning with Event Correlation for Video Question Answering

no code implementations20 Dec 2023 Chengxiang Yin, Zhengping Che, Kun Wu, Zhiyuan Xu, Qinru Qiu, Jian Tang

Video Question Answering (VideoQA) is a very attractive and challenging research direction aiming to understand complex semantics of heterogeneous data from two domains, i. e., the spatio-temporal video content and the word sequence in question.

Question Answering Video Question Answering

Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering

no code implementations20 Dec 2023 Chengxiang Yin, Zhengping Che, Kun Wu, Zhiyuan Xu, Jian Tang

Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature.

Question Answering Visual Question Answering

DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Field

no code implementations4 Aug 2023 Haowen Wang, Zhipeng Fan, Zhen Zhao, Zhengping Che, Zhiyuan Xu, Dong Liu, Feifei Feng, Yakun Huang, XIUQUAN QIAO, Jian Tang

We introduce a pose regression module that shares the deformation features and template codes from the fields to estimate the accurate 6D pose of each object in the scene.

Object Pose Estimation

RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion

no code implementations6 Jun 2023 Haowen Wang, Zhengping Che, Mingyuan Wang, Zhiyuan Xu, XIUQUAN QIAO, Mengshi Qi, Feifei Feng, Jian Tang

The raw depth image captured by indoor depth sensors usually has an extensive range of missing depth values due to inherent limitations such as the inability to perceive transparent objects and the limited distance range.

Depth Completion Transparent objects

CP$^3$: Channel Pruning Plug-in for Point-based Networks

no code implementations23 Mar 2023 Yaomin Huang, Ning Liu, Zhengping Che, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Guixu Zhang, Xinmei Liu, Feifei Feng, Jian Tang

CP$^3$ is elaborately designed to leverage the characteristics of point clouds and PNNs in order to enable 2D channel pruning methods for PNNs.

CP3: Channel Pruning Plug-In for Point-Based Networks

no code implementations CVPR 2023 Yaomin Huang, Ning Liu, Zhengping Che, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Guixu Zhang, Xinmei Liu, Feifei Feng, Jian Tang

Directly implementing the 2D CNN channel pruning methods to PNNs undermine the performance of PNNs because of the different representations of 2D images and 3D point clouds as well as the network architecture disparity.

Label-Guided Auxiliary Training Improves 3D Object Detector

1 code implementation24 Jul 2022 Yaomin Huang, Xinmei Liu, Yichen Zhu, Zhiyuan Xu, Chaomin Shen, Zhengping Che, Guixu Zhang, Yaxin Peng, Feifei Feng, Jian Tang

Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently.

3D Object Detection Object +1

I-SEA: Importance Sampling and Expected Alignment-Based Deep Distance Metric Learning for Time Series Analysis and Embedding

1 code implementation Proceedings of the AAAI Conference on Artificial Intelligence 2022 Sirisha Rambhatla, Zhengping Che, Yan Liu

To this end, we develop an Importance Sampling based distance metric -- I-SEA -- which enjoys the properties of a metric while consistently achieving superior performance for machine learning tasks such as classification and representation learning.

Density Estimation Metric Learning +4

RGB-Depth Fusion GAN for Indoor Depth Completion

no code implementations CVPR 2022 Haowen Wang, Mingyuan Wang, Zhengping Che, Zhiyuan Xu, XIUQUAN QIAO, Mengshi Qi, Feifei Feng, Jian Tang

In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map.

Depth Completion Transparent objects

CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving

1 code implementation17 Feb 2022 Yinuo Zhao, Kun Wu, Zhiyuan Xu, Zhengping Che, Qi Lu, Jian Tang, Chi Harold Liu

Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors.

reinforcement-learning Reinforcement Learning (RL)

CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization

no code implementations21 Oct 2021 Wenzheng Hu, Zhengping Che, Ning Liu, Mingyang Li, Jian Tang, ChangShui Zhang, Jianqiang Wang

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks.

Human Pose Transfer with Augmented Disentangled Feature Consistency

no code implementations23 Jul 2021 Kun Wu, Chengxiang Yin, Zhengping Che, Bo Jiang, Jian Tang, Zheng Guan, Gangyi Ding

Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others.

Data Augmentation Pose Transfer

Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?

no code implementations19 Feb 2021 Ning Liu, Geng Yuan, Zhengping Che, Xuan Shen, Xiaolong Ma, Qing Jin, Jian Ren, Jian Tang, Sijia Liu, Yanzhi Wang

In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i. e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network.

Model Compression

Hierarchical Graph Attention Network for Few-Shot Visual-Semantic Learning

no code implementations ICCV 2021 Chengxiang Yin, Kun Wu, Zhengping Che, Bo Jiang, Zhiyuan Xu, Jian Tang

Deep learning has made tremendous success in computer vision, natural language processing and even visual-semantic learning, which requires a huge amount of labeled training data.

Graph Attention Image Captioning +2

Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction

no code implementations5 Nov 2020 Xuanzhao Wang, Zhengping Che, Bo Jiang, Ning Xiao, Ke Yang, Jian Tang, Jieping Ye, Jingyu Wang, Qi Qi

In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos.

Anomaly Detection Video Anomaly Detection

Fast Object Detection with Latticed Multi-Scale Feature Fusion

no code implementations5 Nov 2020 Yue Shi, Bo Jiang, Zhengping Che, Jian Tang

In this work, we present a novel module, the Fluff block, to alleviate drawbacks of current multi-scale fusion methods and facilitate multi-scale object detection.

Object object-detection +1

DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search

no code implementations4 Nov 2020 Yushuo Guan, Ning Liu, Pengyu Zhao, Zhengping Che, Kaigui Bian, Yanzhi Wang, Jian Tang

The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment.

Neural Architecture Search

Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control

1 code implementation NeurIPS 2020 Zhiyuan Xu, Kun Wu, Zhengping Che, Jian Tang, Jieping Ye

While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks.

Continuous Control reinforcement-learning +2

D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios

no code implementations3 Apr 2019 Zhengping Che, Guangyu Li, Tracy Li, Bo Jiang, Xuefeng Shi, Xinsheng Zhang, Ying Lu, Guobin Wu, Yan Liu, Jieping Ye

Driving datasets accelerate the development of intelligent driving and related computer vision technologies, while substantial and detailed annotations serve as fuels and powers to boost the efficacy of such datasets to improve learning-based models.

Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series

no code implementations ICML 2018 Zhengping Che, Sanjay Purushotham, Guangyu Li, Bo Jiang, Yan Liu

Multi-Rate Multivariate Time Series (MR-MTS) are the multivariate time series observations which come with various sampling rates and encode multiple temporal dependencies.

Time Series Time Series Analysis

Relational Multi-Instance Learning for Concept Annotation from Medical Time Series

no code implementations ICLR 2018 Sanjay Purushotham, Zhengping Che, Bo Jiang, Tanachat Nilanon, Yan Liu

Recent advances in computing technology and sensor design have made it easier to collect longitudinal or time series data from patients, resulting in a gigantic amount of available medical data.

Time Series Time Series Analysis

Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets

1 code implementation23 Oct 2017 Sanjay Purushotham, Chuizheng Meng, Zhengping Che, Yan Liu

Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications.

Benchmarking BIG-bench Machine Learning +6

Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records

no code implementations6 Sep 2017 Zhengping Che, Yu Cheng, Shuangfei Zhai, Zhaonan Sun, Yan Liu

We use this generative model together with a convolutional neural network (CNN) based prediction model to improve the onset prediction performance.

Generative Adversarial Network

Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding

no code implementations25 Jan 2017 Zhengping Che, Yu Cheng, Zhaonan Sun, Yan Liu

To account for high dimensionality, we use the embedding medical features in the CNN model which hold the natural medical concepts.

Distilling Knowledge from Deep Networks with Applications to Healthcare Domain

no code implementations11 Dec 2015 Zhengping Che, Sanjay Purushotham, Robinder Khemani, Yan Liu

Exponential growth in Electronic Healthcare Records (EHR) has resulted in new opportunities and urgent needs for discovery of meaningful data-driven representations and patterns of diseases in Computational Phenotyping research.

Computational Phenotyping Decision Making +4

Cannot find the paper you are looking for? You can Submit a new open access paper.