Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Shanghang Zhang

Shanghang Zhang

UC Berkeley

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation


Mar 31, 2021
Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni Vincentelli

Figure 1 for Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Figure 2 for Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Figure 3 for Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Figure 4 for Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
* CVPR 2021 
  Access Paper or Ask Questions

Self-Supervised Pretraining Improves Self-Supervised Pretraining


Mar 25, 2021
Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell

Figure 1 for Self-Supervised Pretraining Improves Self-Supervised Pretraining
Figure 2 for Self-Supervised Pretraining Improves Self-Supervised Pretraining
Figure 3 for Self-Supervised Pretraining Improves Self-Supervised Pretraining
Figure 4 for Self-Supervised Pretraining Improves Self-Supervised Pretraining

  Access Paper or Ask Questions

P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding


Dec 24, 2020
Yunze Liu, Li Yi, Shanghang Zhang, Qingnan Fan, Thomas Funkhouser, Hao Dong

Figure 1 for P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding
Figure 2 for P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding
Figure 3 for P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding
Figure 4 for P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding

  Access Paper or Ask Questions

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting


Dec 17, 2020
Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, Wancai Zhang

Figure 1 for Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Figure 2 for Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Figure 3 for Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Figure 4 for Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
* 7 pages (main), 5 pages (appendix) and to be appeared in AAAI2021 
  Access Paper or Ask Questions

Cross-Domain Sentiment Classification with In-Domain Contrastive Learning


Dec 05, 2020
Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer

Figure 1 for Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
Figure 2 for Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
Figure 3 for Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
Figure 4 for Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
* 10pages, 2 figures, accepted to NeurIPS 2020 Workshop on Self-supervised Learning. arXiv admin note: text overlap with arXiv:2010.16088 
  Access Paper or Ask Questions

Annotation-Efficient Untrimmed Video Action Recognition


Nov 30, 2020
Yixiong Zou, Shanghang Zhang, Guangyao Chen, Yonghong Tian, Kurt Keutzer, José M. F. Moura

Figure 1 for Annotation-Efficient Untrimmed Video Action Recognition
Figure 2 for Annotation-Efficient Untrimmed Video Action Recognition
Figure 3 for Annotation-Efficient Untrimmed Video Action Recognition
Figure 4 for Annotation-Efficient Untrimmed Video Action Recognition

  Access Paper or Ask Questions

Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization


Nov 12, 2020
Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer

Figure 1 for Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization
Figure 2 for Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization
Figure 3 for Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization
Figure 4 for Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization
* 5 pages, 1 figure 
  Access Paper or Ask Questions

Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization


Oct 30, 2020
Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer

Figure 1 for Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization
Figure 2 for Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization
Figure 3 for Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization
Figure 4 for Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization

  Access Paper or Ask Questions

Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation


Oct 12, 2020
Bo Li, Yezhen Wang, Shanghang Zhang, Dongsheng Li, Trevor Darrell, Kurt Keutzer, Han Zhao

Figure 1 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
Figure 2 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
Figure 3 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
Figure 4 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
* Preprint 
  Access Paper or Ask Questions

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation


Sep 19, 2020
Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer

Figure 1 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Figure 2 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Figure 3 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Figure 4 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

  Access Paper or Ask Questions

Instance Adaptive Self-Training for Unsupervised Domain Adaptation


Aug 27, 2020
Ke Mei, Chuang Zhu, Jiaqi Zou, Shanghang Zhang

Figure 1 for Instance Adaptive Self-Training for Unsupervised Domain Adaptation
Figure 2 for Instance Adaptive Self-Training for Unsupervised Domain Adaptation
Figure 3 for Instance Adaptive Self-Training for Unsupervised Domain Adaptation
Figure 4 for Instance Adaptive Self-Training for Unsupervised Domain Adaptation
* ECCV 2020 
  Access Paper or Ask Questions

Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition


Aug 07, 2020
Yixiong Zou, Shanghang Zhang, José M. F. Moura, JianPeng Yu, Yonghong Tian

Figure 1 for Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition
Figure 2 for Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition
Figure 3 for Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition
Figure 4 for Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition

  Access Paper or Ask Questions

TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning


Jul 14, 2020
Xinwei Sun, Yilun Xu, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang

Figure 1 for TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
Figure 2 for TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
Figure 3 for TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
Figure 4 for TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
* ECCV 2020 (oral) 
  Access Paper or Ask Questions

Rethinking Distributional Matching Based Domain Adaptation


Jul 03, 2020
Bo Li, Yezhen Wang, Tong Che, Shanghang Zhang, Sicheng Zhao, Pengfei Xu, Wei Zhou, Yoshua Bengio, Kurt Keutzer

Figure 1 for Rethinking Distributional Matching Based Domain Adaptation
Figure 2 for Rethinking Distributional Matching Based Domain Adaptation
Figure 3 for Rethinking Distributional Matching Based Domain Adaptation
Figure 4 for Rethinking Distributional Matching Based Domain Adaptation
* Preprint version 
  Access Paper or Ask Questions

Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigms


Jun 19, 2020
Xingyi Yang, Xuehai He, Yuxiao Liang, Yue Yang, Shanghang Zhang, Pengtao Xie

Figure 1 for Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigms
Figure 2 for Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigms
Figure 3 for Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigms
Figure 4 for Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigms

  Access Paper or Ask Questions

Compositional Few-Shot Recognition with Primitive Discovery and Enhancing


May 26, 2020
Yixiong Zou, Shanghang Zhang, Ke Chen, José M. F. Moura, Yaowei Wang, Yonghong Tian

Figure 1 for Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
Figure 2 for Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
Figure 3 for Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
Figure 4 for Compositional Few-Shot Recognition with Primitive Discovery and Enhancing

  Access Paper or Ask Questions

Decoupling Global and Local Representations from/for Image Generation


Apr 12, 2020
Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy

Figure 1 for Decoupling Global and Local Representations from/for Image Generation
Figure 2 for Decoupling Global and Local Representations from/for Image Generation
Figure 3 for Decoupling Global and Local Representations from/for Image Generation
Figure 4 for Decoupling Global and Local Representations from/for Image Generation
* First version of preprint. 22 pages (plus appendix), 16 figures, 5 tables. Due to arxiv size constraints, this version is using downscaled images. Please download the full-resolution version from https://vixra.org/abs/2004.0222 
  Access Paper or Ask Questions

Decoupling Features and Coordinates for Few-shot RGB Relocalization


Nov 26, 2019
Siyan Dong, Songyin Wu, Yixin Zhuang, Shanghang Zhang, Kai Xu, Baoquan Chen

Figure 1 for Decoupling Features and Coordinates for Few-shot RGB Relocalization
Figure 2 for Decoupling Features and Coordinates for Few-shot RGB Relocalization
Figure 3 for Decoupling Features and Coordinates for Few-shot RGB Relocalization
Figure 4 for Decoupling Features and Coordinates for Few-shot RGB Relocalization
* 8 pages 
  Access Paper or Ask Questions

Multi-source Distilling Domain Adaptation


Nov 22, 2019
Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer

Figure 1 for Multi-source Distilling Domain Adaptation
Figure 2 for Multi-source Distilling Domain Adaptation
Figure 3 for Multi-source Distilling Domain Adaptation
Figure 4 for Multi-source Distilling Domain Adaptation
* Accepted by AAAI 2020 
  Access Paper or Ask Questions

Generalized Zero-shot ICD Coding


Sep 28, 2019
Congzheng Song, Shanghang Zhang, Najmeh Sadoughi, Pengtao Xie, Eric Xing

Figure 1 for Generalized Zero-shot ICD Coding
Figure 2 for Generalized Zero-shot ICD Coding
Figure 3 for Generalized Zero-shot ICD Coding
Figure 4 for Generalized Zero-shot ICD Coding

  Access Paper or Ask Questions

Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning


Jul 12, 2019
Jian Ni, Shanghang Zhang, Haiyong Xie

Figure 1 for Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
Figure 2 for Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
Figure 3 for Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
Figure 4 for Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
* 10 pages, 5 figures, 
  Access Paper or Ask Questions

Hierarchical Attention Networks for Knowledge Base Completion via Joint Adversarial Training


Oct 14, 2018
Chen Li, Xutan Peng, Shanghang Zhang, Jianxin Li, Lihong Wang

Figure 1 for Hierarchical Attention Networks for Knowledge Base Completion via Joint Adversarial Training
Figure 2 for Hierarchical Attention Networks for Knowledge Base Completion via Joint Adversarial Training
Figure 3 for Hierarchical Attention Networks for Knowledge Base Completion via Joint Adversarial Training
Figure 4 for Hierarchical Attention Networks for Knowledge Base Completion via Joint Adversarial Training

  Access Paper or Ask Questions

Topology Adaptive Graph Convolutional Networks


Feb 11, 2018
Jian Du, Shanghang Zhang, Guanhang Wu, Jose M. F. Moura, Soummya Kar

Figure 1 for Topology Adaptive Graph Convolutional Networks
Figure 2 for Topology Adaptive Graph Convolutional Networks
Figure 3 for Topology Adaptive Graph Convolutional Networks
Figure 4 for Topology Adaptive Graph Convolutional Networks
* 13 pages 
  Access Paper or Ask Questions

Multiple Source Domain Adaptation with Adversarial Training of Neural Networks


Oct 27, 2017
Han Zhao, Shanghang Zhang, Guanhang Wu, João P. Costeira, José M. F. Moura, Geoffrey J. Gordon

Figure 1 for Multiple Source Domain Adaptation with Adversarial Training of Neural Networks
Figure 2 for Multiple Source Domain Adaptation with Adversarial Training of Neural Networks
Figure 3 for Multiple Source Domain Adaptation with Adversarial Training of Neural Networks
Figure 4 for Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

  Access Paper or Ask Questions

FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras


Aug 01, 2017
Shanghang Zhang, Guanhang Wu, João P. Costeira, José M. F. Moura

Figure 1 for FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
Figure 2 for FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
Figure 3 for FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
Figure 4 for FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
* Accepted by International Conference on Computer Vision (ICCV), 2017 
  Access Paper or Ask Questions