no code implementations • ICML 2020 • Yibo Yang, Robert Bamler, Stephan Mandt
Deep Bayesian latent variable models have enabled new approaches to both model and data compression.
1 code implementation • 18 Mar 2024 • Xiaojie Li, Yibo Yang, Xiangtai Li, Jianlong Wu, Yue Yu, Bernard Ghanem, Min Zhang
To tackle these challenges, we present GenView, a controllable framework that augments the diversity of positive views leveraging the power of pretrained generative models while preserving semantics.
1 code implementation • 18 Jan 2024 • Shilin Xu, Haobo Yuan, Qingyu Shi, Lu Qi, Jingbo Wang, Yibo Yang, Yining Li, Kai Chen, Yunhai Tong, Bernard Ghanem, Xiangtai Li, Ming-Hsuan Yang
Segment Anything Model (SAM) is one remarkable model that can achieve generalized segmentation.
no code implementations • 12 Oct 2023 • Peifeng Gao, Qianqian Xu, Yibo Yang, Peisong Wen, Huiyang Shao, Zhiyong Yang, Bernard Ghanem, Qingming Huang
While there have been extensive studies on optimization characteristics showing the global optimality of neural collapse, little research has been done on the generalization behaviors during the occurrence of NC.
no code implementations • 2 Sep 2023 • Fengxiang Bie, Yibo Yang, Zhongzhu Zhou, Adam Ghanem, Minjia Zhang, Zhewei Yao, Xiaoxia Wu, Connor Holmes, Pareesa Golnari, David A. Clifton, Yuxiong He, DaCheng Tao, Shuaiwen Leon Song
Text-to-image generation (TTI) refers to the usage of models that could process text input and generate high fidelity images based on text descriptions.
no code implementations • 22 Aug 2023 • Yuxuan Du, Yibo Yang, Tongliang Liu, Zhouchen Lin, Bernard Ghanem, DaCheng Tao
Understanding the dynamics of large quantum systems is hindered by the curse of dimensionality.
1 code implementation • 10 Aug 2023 • Yangyang Xu, Yibo Yang, Bernard Ghanem, Lefei Zhang, Du Bo, DaCheng Tao
In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer with shared gating for multi-task learning of dense prediction.
2 code implementations • 3 Aug 2023 • Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, DaCheng Tao, Bernard Ghanem
Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world implementations and further exacerbate the well-known problem of catastrophic forgetting.
1 code implementation • 28 Jun 2023 • Jianzong Wu, Xiangtai Li, Shilin Xu, Haobo Yuan, Henghui Ding, Yibo Yang, Xia Li, Jiangning Zhang, Yunhai Tong, Xudong Jiang, Bernard Ghanem, DaCheng Tao
To our knowledge, this is the first comprehensive literature review of open vocabulary learning.
1 code implementation • ICCV 2023 • Yibo Yang, Stephan Mandt
We theoretically formalize the intuition behind, and our experimental results establish a new frontier in the trade-off between rate-distortion and decoding complexity for neural image compression.
no code implementations • 27 Mar 2023 • Chenxi Huang, Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai
One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server.
no code implementations • 1 Mar 2023 • Chao Xue, Wei Liu, Shuai Xie, Zhenfang Wang, Jiaxing Li, Xuyang Peng, Liang Ding, Shanshan Zhao, Qiong Cao, Yibo Yang, Fengxiang He, Bohua Cai, Rongcheng Bian, Yiyan Zhao, Heliang Zheng, Xiangyang Liu, Dongkai Liu, Daqing Liu, Li Shen, Chang Li, Shijin Zhang, Yukang Zhang, Guanpu Chen, Shixiang Chen, Yibing Zhan, Jing Zhang, Chaoyue Wang, DaCheng Tao
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
no code implementations • 20 Feb 2023 • Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai, Xiaofei He, Ronghua Liang
Compared to 2D images, 3D point clouds are much more sensitive to rotations.
1 code implementation • 6 Feb 2023 • Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao
In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).
1 code implementation • ICLR 2023 • Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao
In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).
Ranked #3 on Few-Shot Class-Incremental Learning on CUB-200-2011
2 code implementations • 9 Jan 2023 • Yangyang Xu, Yibo Yang, Lefei Zhang
In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer for multi-task learning of dense prediction.
2 code implementations • CVPR 2023 • Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia
Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers.
1 code implementation • 3 Jan 2023 • Xiangtai Li, Shilin Xu, Yibo Yang, Haobo Yuan, Guangliang Cheng, Yunhai Tong, Zhouchen Lin, Ming-Hsuan Yang, DaCheng Tao
Third, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross-attention scheme to boost part segmentation qualities further.
no code implementations • ICCV 2023 • Yangyang Xu, Yibo Yang, Lefei Zhang
With the less sensitive divergence, our knowledge distillation with an alternative match is applied for capturing inter-task and intra-task information between the teacher model and the student model of each task, thereby learning more "dark knowledge" for effective distillation.
no code implementations • 29 Dec 2022 • Yuxuan Du, Yibo Yang, DaCheng Tao, Min-Hsiu Hsieh
Using these findings, we propose a method that uses loss dynamics to probe whether a QC may be more effective than a classical classifier on a particular learning task.
1 code implementation • 12 Oct 2022 • Yibo Yang, Hong Wang, Haobo Yuan, Zhouchen Lin
With NIO, we improve the classification performance of a variety of neural architectures on CIFAR-10, CIFAR-100, and ImageNet.
1 code implementation • 13 Jul 2022 • Zekun Li, Zhengyang Geng, Zhao Kang, Wenyu Chen, Yibo Yang
To understand the instability in training, we detect the gradient flow of attention and observe gradient conflict among attention branches.
1 code implementation • 10 Jul 2022 • Xiangtai Li, Jiangning Zhang, Yibo Yang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, DaCheng Tao
In this paper, we focus on exploring effective methods for faster, accurate, and domain agnostic semantic segmentation.
1 code implementation • 19 Jun 2022 • Jiangning Zhang, Xiangtai Li, Yabiao Wang, Chengjie Wang, Yibo Yang, Yong liu, DaCheng Tao
Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derives that both have consistent mathematical formulation.
1 code implementation • 28 May 2022 • Yangyang Xu, Xiangtai Li, Haobo Yuan, Yibo Yang, Lefei Zhang
We first model each task with a task-relevant query.
no code implementations • 19 Apr 2022 • Liang Xie, Yibo Yang, Deng Cai, Xiaofei He
Class imbalance distribution widely exists in real-world engineering.
1 code implementation • 10 Apr 2022 • Xiangtai Li, Shilin Xu, Yibo Yang, Guangliang Cheng, Yunhai Tong, DaCheng Tao
To the best of our knowledge, we are the first to solve the PPS problem via \textit{a unified and end-to-end transformer model.
1 code implementation • 17 Mar 2022 • Yibo Yang, Shixiang Chen, Xiangtai Li, Liang Xie, Zhouchen Lin, DaCheng Tao
Modern deep neural networks for classification usually jointly learn a backbone for representation and a linear classifier to output the logit of each class.
Ranked #26 on Long-tail Learning on CIFAR-10-LT (ρ=100)
1 code implementation • CVPR 2022 • Robin Wang, Yibo Yang, DaCheng Tao
Specifically, our proposed framework named ART-Point regards the rotation of the point cloud as an attack and improves rotation robustness by training the classifier on inputs with Adversarial RoTations.
1 code implementation • 6 Mar 2022 • Yibo Yang, Georgios Kissas, Paris Perdikaris
Finally, we provide an optimized JAX library called {\em UQDeepONet} that can accommodate large model architectures, large ensemble sizes, as well as large data-sets with excellent parallel performance on accelerated hardware, thereby enabling uncertainty quantification for DeepONets in realistic large-scale applications.
2 code implementations • 14 Feb 2022 • Yibo Yang, Stephan Mandt, Lucas Theis
Neural compression is the application of neural networks and other machine learning methods to data compression.
3 code implementations • 13 Jan 2022 • Qianyu Zhou, Xiangtai Li, Lu He, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lizhuang Ma, DaCheng Tao
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
Ranked #4 on Video Object Detection on ImageNet VID (using extra training data)
1 code implementation • 5 Dec 2021 • Haobo Yuan, Xiangtai Li, Yibo Yang, Guangliang Cheng, Jing Zhang, Yunhai Tong, Lefei Zhang, DaCheng Tao
The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously.
no code implementations • 4 Dec 2021 • Xinke Ma, Yibo Yang, Yong Xia, DaCheng Tao
In this paper, we present a novel dual-flow transformation network with region consistency constraint which maximizes the similarity of ROIs within a pair of images and estimates both global and region spatial transformations simultaneously.
2 code implementations • ICLR 2022 • Yibo Yang, Stephan Mandt
By contrast, this paper makes the first attempt at an algorithm for sandwiching the R-D function of a general (not necessarily discrete) source requiring only i. i. d.
1 code implementation • 14 Oct 2021 • Conghao Wong, Beihao Xia, Ziming Hong, Qinmu Peng, Wei Yuan, Qiong Cao, Yibo Yang, Xinge You
Different frequency bands in the trajectory spectrums could hierarchically reflect agents' motion preferences at different scales.
Ranked #3 on Trajectory Prediction on ETH/UCY
1 code implementation • 30 Sep 2021 • Mufeng Tang, Yibo Yang, Yali Amit
We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks.
1 code implementation • 28 Jul 2021 • Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images.
1 code implementation • 28 Jul 2021 • Xiangtai Li, Hao He, Yibo Yang, Henghui Ding, Kuiyuan Yang, Guangliang Cheng, Yunhai Tong, DaCheng Tao
To incorporate both temporal and scale information, we propose a Temporal Pyramid Routing (TPR) strategy to conditionally align and conduct pixel-level aggregation from a feature pyramid pair of two adjacent frames.
1 code implementation • 25 May 2021 • Hao He, Xiangtai Li, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lubin Weng, Zhouchen Lin, Shiming Xiang
This module is used to squeeze the object boundary from both inner and outer directions, which contributes to precise mask representation.
no code implementations • ICLR Workshop Neural_Compression 2021 • Yibo Yang, Stephan Mandt
The rate-distortion function tells us the minimal number of bits on average to compress a random object within a given distortion tolerance.
no code implementations • ICLR Workshop Neural_Compression 2021 • Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
There has been a recent surge of interest in neural video compression models that combines data-driven dimensionality reduction with learned entropy coding.
1 code implementation • 19 Feb 2021 • Yibo Yang, Antoine Blanchard, Themistoklis Sapsis, Paris Perdikaris
We present a new type of acquisition functions for online decision making in multi-armed and contextual bandit problems with extreme payoffs.
no code implementations • CVPR 2021 • Yibo Yang, Shan You, Hongyang Li, Fei Wang, Chen Qian, Zhouchen Lin
Our method enables differentiable sparsification, and keeps the derived architecture equivalent to that of Engine-cell, which further improves the consistency between search and evaluation.
no code implementations • 1 Jan 2021 • Yibo Yang, Shan You, Hongyang Li, Fei Wang, Chen Qian, Zhouchen Lin
The Engine-cell is differentiable for architecture search, while the Transit-cell only transits the current sub-graph by architecture derivation.
no code implementations • 1 Jan 2021 • Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang
Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types.
no code implementations • pproximateinference AABI Symposium 2021 • Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.
no code implementations • 18 Nov 2020 • Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang
However, even for this consistent search, the searched cells often suffer from poor performance, especially for the supernet with fewer layers, as current DARTS methods are prone to wide and shallow cells, and this topology collapse induces sub-optimal searched cells.
3 code implementations • ICLR 2021 • Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.
1 code implementation • NeurIPS 2020 • Yibo Yang, Hongyang Li, Shan You, Fei Wang, Chen Qian, Zhouchen Lin
By doing so, our network for search at each update satisfies the sparsity constraint and is efficient to train.
2 code implementations • NeurIPS 2020 • Yibo Yang, Robert Bamler, Stephan Mandt
We consider the problem of lossy image compression with deep latent variable models.
1 code implementation • 15 Apr 2020 • Yibo Yang, Mohamed Aziz Bhouri, Paris Perdikaris
This paper presents a machine learning framework for Bayesian systems identification from noisy, sparse and irregular observations of nonlinear dynamical systems.
no code implementations • CVPR 2020 • Xia Li, Yibo Yang, Qijie Zhao, Tiancheng Shen, Zhouchen Lin, Hong Liu
The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation.
2 code implementations • ICML 2020 • Yibo Yang, Robert Bamler, Stephan Mandt
Our experimental results demonstrate the importance of taking into account posterior uncertainties, and show that image compression with the proposed algorithm outperforms JPEG over a wide range of bit rates using only a single standard VAE.
1 code implementation • 8 Jan 2020 • Yuqiao Chen, Yibo Yang, Sriraam Natarajan, Nicholas Ruozzi
We demonstrate that the proposed variational methods are both scalable and can take advantage of approximate model symmetries, even in the presence of a large amount of continuous evidence.
no code implementations • 23 Nov 2019 • Yibo Yang, Jianlong Wu, Hongyang Li, Xia Li, Tiancheng Shen, Zhouchen Lin
We establish a stability condition for ResNets with step sizes and weight parameters, and point out the effects of step sizes on the stability and performance.
1 code implementation • 18 Nov 2019 • Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin
In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances.
Ranked #8 on Panoptic Segmentation on Cityscapes test
5 code implementations • ICCV 2019 • Xia Li, Zhisheng Zhong, Jianlong Wu, Yibo Yang, Zhouchen Lin, Hong Liu
It is designed to compute the representation of each position by a weighted sum of the features at all positions.
Ranked #11 on Semantic Segmentation on COCO-Stuff test
1 code implementation • 13 May 2019 • Georgios Kissas, Yibo Yang, Eileen Hwuang, Walter R. Witschey, John A. Detre, Paris Perdikaris
Such models can be nowadays deployed on large patient-specific topologies of systemic arterial networks and return detailed predictions on flow patterns, wall shear stresses, and pulse wave propagation.
2 code implementations • 15 Jan 2019 • Yibo Yang, Paris Perdikaris
We present a probabilistic deep learning methodology that enables the construction of predictive data-driven surrogates for stochastic systems.
no code implementations • 9 Dec 2018 • Yibo Yang, Paris Perdikaris
We consider the application of deep generative models in propagating uncertainty through complex physical systems.
2 code implementations • 9 Nov 2018 • Yibo Yang, Paris Perdikaris
We present a deep learning framework for quantifying and propagating uncertainty in systems governed by non-linear differential equations using physics-informed neural networks.
no code implementations • 3 Oct 2018 • Huan Li, Yibo Yang, Dongmin Chen, Zhouchen Lin
In this paper, we propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a faster optimization algorithm may lead to a better neural network structure.
no code implementations • NeurIPS 2018 • Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang
To solve these problems, we propose the Super-Resolution CliqueNet (SRCliqueNet) to reconstruct the high resolution (HR) image with better textural details in the wavelet domain.
no code implementations • 14 Jun 2018 • Yibo Yang, Nicholas Ruozzi, Vibhav Gogate
We propose a simple and easy to implement neural network compression algorithm that achieves results competitive with more complicated state-of-the-art methods.
3 code implementations • CVPR 2018 • Yibo Yang, Zhisheng Zhong, Tiancheng Shen, Zhouchen Lin
In contrast to prior networks, there are both forward and backward connections between any two layers in the same block.
no code implementations • ICLR 2018 • Yibo Yang, Nicholas Ruozzi, Vibhav Gogate
Recently, there has been growing interest in methods that perform neural network compression, namely techniques that attempt to substantially reduce the size of a neural network without significant reduction in performance.