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 Jiashi Feng

Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-Supervision


Jul 20, 2021
Yifan Zhang, Bryan Hooi, Lanqing Hong, Jiashi Feng


  Access Paper or Ask Questions

Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing


Jul 12, 2021
Kaixin Wang, Kuangqi Zhou, Qixin Zhang, Jie Shao, Bryan Hooi, Jiashi Feng

* ICML 2021 

  Access Paper or Ask Questions

Recovering the Unbiased Scene Graphs from the Biased Ones


Jul 05, 2021
Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, Jiashi Feng

* Accepted by ACMMM 2021. Source code will be available at https://github.com/coldmanck/recovering-unbiased-scene-graphs 

  Access Paper or Ask Questions

VOLO: Vision Outlooker for Visual Recognition


Jun 28, 2021
Li Yuan, Qibin Hou, Zihang Jiang, Jiashi Feng, Shuicheng Yan

* code: https://github.com/sail-sg/volo 

  Access Paper or Ask Questions

LV-BERT: Exploiting Layer Variety for BERT


Jun 25, 2021
Weihao Yu, Zihang Jiang, Fei Chen, Qibin Hou, Jiashi Feng

* Accepted to Findings of ACL 2021. The code and pre-trained models are available at https://github.com/yuweihao/LV-BERT 

  Access Paper or Ask Questions

Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition


Jun 23, 2021
Qibin Hou, Zihang Jiang, Li Yuan, Ming-Ming Cheng, Shuicheng Yan, Jiashi Feng

* 9 pages 

  Access Paper or Ask Questions

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data


Jun 09, 2021
Mi Luo, Fei Chen, Dapeng Hu, Yifan Zhang, Jian Liang, Jiashi Feng

* 21 pages 

  Access Paper or Ask Questions

Refiner: Refining Self-attention for Vision Transformers


Jun 07, 2021
Daquan Zhou, Yujun Shi, Bingyi Kang, Weihao Yu, Zihang Jiang, Yuan Li, Xiaojie Jin, Qibin Hou, Jiashi Feng


  Access Paper or Ask Questions

Image-to-Video Generation via 3D Facial Dynamics


May 31, 2021
Xiaoguang Tu, Yingtian Zou, Jian Zhao, Wenjie Ai, Jian Dong, Yuan Yao, Zhikang Wang, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng


  Access Paper or Ask Questions

PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal


May 26, 2021
Si Liu, Wentao Jiang, Chen Gao, Ran He, Jiashi Feng, Bo Li, Shuicheng Yan

* Accepted by TPAMI 2021 

  Access Paper or Ask Questions

ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos


May 25, 2021
Meng-Jiun Chiou, Chun-Yu Liao, Li-Wei Wang, Roger Zimmermann, Jiashi Feng

* Accepted at ACM ICMR'21 Workshop on Intelligent Cross-Data Analysis and Retrieval. The dataset and source code are available at https://github.com/coldmanck/VidHOI 

  Access Paper or Ask Questions

Joint Face Image Restoration and Frontalization for Recognition


May 12, 2021
Xiaoguang Tu, Jian Zhao, Qiankun Liu, Wenjie Ai, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng

* 14 pages, 9 figures 

  Access Paper or Ask Questions

Continual Learning via Bit-Level Information Preserving


May 10, 2021
Yujun Shi, Li Yuan, Yunpeng Chen, Jiashi Feng

* CVPR2021 

  Access Paper or Ask Questions

Body Meshes as Points


May 06, 2021
Jianfeng Zhang, Dongdong Yu, Jun Hao Liew, Xuecheng Nie, Jiashi Feng

* To appear at CVPR 2021 

  Access Paper or Ask Questions

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation


May 06, 2021
Kehong Gong, Jianfeng Zhang, Jiashi Feng

* CVPR 2021 Oral Paper, code available: https://github.com/jfzhang95/PoseAug 

  Access Paper or Ask Questions

How Well Self-Supervised Pre-Training Performs with Streaming Data?


Apr 25, 2021
Dapeng Hu, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Alfred Shen, Jiashi Feng

* 16 pages; 16figures 

  Access Paper or Ask Questions

Token Labeling: Training a 85.4% Top-1 Accuracy Vision Transformer with 56M Parameters on ImageNet


Apr 23, 2021
Zihang Jiang, Qibin Hou, Li Yuan, Daquan Zhou, Xiaojie Jin, Anran Wang, Jiashi Feng


  Access Paper or Ask Questions

DeepViT: Towards Deeper Vision Transformer


Apr 19, 2021
Daquan Zhou, Bingyi Kang, Xiaojie Jin, Linjie Yang, Xiaochen Lian, Zihang Jiang, Qibin Hou, Jiashi Feng


  Access Paper or Ask Questions

Distill and Fine-tune: Effective Adaptation from a Black-box Source Model


Apr 04, 2021
Jian Liang, Dapeng Hu, Ran He, Jiashi Feng


  Access Paper or Ask Questions

Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation


Mar 30, 2021
Shuning Chang, Pichao Wang, Fan Wang, Hao Li, Jiashi Feng

* 12 pagess, 4 figures 

  Access Paper or Ask Questions

AutoSpace: Neural Architecture Search with Less Human Interference


Mar 22, 2021
Daquan Zhou, Xiaojie Jin, Xiaochen Lian, Linjie Yang, Yujing Xue, Qibin Hou, Jiashi Feng


  Access Paper or Ask Questions

Coordinate Attention for Efficient Mobile Network Design


Mar 04, 2021
Qibin Hou, Daquan Zhou, Jiashi Feng

* CVPR2021 

  Access Paper or Ask Questions

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning


Feb 12, 2021
Yifan Zhang, Bryan Hooi, Dapeng Hu, Jian Liang, Jiashi Feng


  Access Paper or Ask Questions

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection


Feb 10, 2021
Hanshu Yan, Jingfeng Zhang, Gang Niu, Jiashi Feng, Vincent Y. F. Tan, Masashi Sugiyama


  Access Paper or Ask Questions

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet


Jan 28, 2021
Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Francis EH Tay, Jiashi Feng, Shuicheng Yan

* codes: https://github.com/yitu-opensource/T2T-ViT 

  Access Paper or Ask Questions

ORDNet: Capturing Omni-Range Dependencies for Scene Parsing


Jan 11, 2021
Shaofei Huang, Si Liu, Tianrui Hui, Jizhong Han, Bo Li, Jiashi Feng, Shuicheng Yan

* IEEE Transactions on Image Processing, 2020, 29: 8251-8263 
* Published at TIP 

  Access Paper or Ask Questions

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer


Dec 14, 2020
Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, Jiashi Feng

* arXiv admin note: text overlap with arXiv:2002.08546 

  Access Paper or Ask Questions