Jerry He(ZeBang,He)’s homepage

I receive my BSc Degree from the Computer Department, CSU(Central South University), and MSc Degree from the Computer Engineering Department, City University of Hong Kong. Currently, I am the intern of the ASTRI, and my major direction is Medical Image Analysis.

In the stage of school, my research interests including salient object detection, image layer separation.

Recently my interests change to Object Detection and Segmentation in medical image analysis based on my work.

Beyond, I have some interests in the interesting Visual Application of the video game and the Virtual character. And some of the interesting applications will also be introduced in the latter part.

Domain Adaption is not my interest currently. However I find that the algorithms in the real-world perform badly in Game/Virtual Scenes, therefore, I will consider if the domain adaption methods can solve the problem of the domain gap.

Publication Currently

Lin, Jiaying, Zebang He and Rynson W. H. Lau. “Rich Context Aggregation with Reflection Prior for Glass Surface Detection.” . CVPR2021 (Thanks for them to help with the first paper which I have joined.)

Unofficial Implementation of some papers

Re-implementation of image restoration:

CRRN: Multi-Scale Guided Concurrent Reflection Removal Network, Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Alex C. Kot

https://arxiv.org/abs/1805.11802

https://github.com/He-jerry/CRRN

Learning to Jointly Generate and Separate Reflections, Daiqian Ma, Renjie Wan, Boxin Shi, Alex C. Kot, Ling-Yu Duan

https://openaccess.thecvf.com/content_ICCV_2019/papers/Ma_Learning_to_Jointly_Generate_and_Separate_Reflections_ICCV_2019_paper.pdf

https://github.com/He-jerry/Joint

Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images, Zhengxia Zou, Sen Lei, Tianyang Shi, Zhenwei Shi, Jieping Ye

https://openaccess.thecvf.com/content_CVPR_2020/html/Zou_Deep_Adversarial_Decomposition_A_Unified_Framework_for_Separating_Superimposed_Images_CVPR_2020_paper.html

Official Implementation(Updated Nov 2020, thanks the official code for authors to help me correct some mistakes in the implementation of the code): https://github.com/jiupinjia/Deep-adversarial-decomposition

My unofficial implementation: https://github.com/He-jerry/PatchGAN (Please refer the official implementation first, because my implementation also has some mistakes in training.)

Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal, Jifeng Wang, Xiang Li,Jian Yang

https://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Stacked_Conditional_Generative_CVPR_2018_paper.pdf

Official Implementation (no code)：https://github.com/DeepInsight-PCALab/ST-CGAN

My implementation: https://github.com/He-jerry/ST-CGAN

Residual Squeeze-and-Excitation Network for Fast Image Deraining, Jun Fu, Jianfeng Xu, Kazuyuki Tasaka, Zhibo Chen

https://arxiv.org/abs/2006.00757

https://github.com/He-jerry/Residual-SE-Network

Re-implementation of Saliency Detection:

ResNeSt: Split-Attention Networks, Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Zhi Zhang, Haibin Lin, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander Smola

Deeply Supervised Salient Object Detection with Short Connections, Qibin Hou, Ming-Ming Cheng, Xiao-Wei Hu, Ali Borji, Zhuowen Tu, Philip Torr

ResNeSt

DSSNet

https://github.com/He-jerry/DSSNet

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection,Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R. Zaiane and Martin Jagersand

https://arxiv.org/pdf/2005.09007.pdf

official implementation(Pytorch):https://github.com/xuebinqin/U-2-Net

My unofficial implementation(Tensorflow):https://github.com/He-jerry/U2Net-Tensorflow

F3Net: Fusion, Feedback and Focus for Salient Object Detection,Jun Wei, Shuhui Wang, Qingming Huang

https://arxiv.org/abs/1911.11445

official implementation(Pytorch):https://github.com/weijun88/F3Net

My unofficial implementation(Tensorflow):https://github.com/He-jerry/F3Net-Tensorflow