Left Image

Github @Aitical

Wechat @w965813422

Gang Wu (吴刚)

PhD student @ HIT

I obtained my Bachelor degree from Soochow University in 2020.

Currently, I am a Ph.D. student at Harbin Institute of Technology, where I am under the supervision of Prof. Junjun Jiang.

Mainly intrest in computer vision, especially in Low-level Vision and Representation Learning.


News

  • 2024-09: One first author paper was accepted in IEEE Transactions on Image Processing.
  • 2024-07: One first author paper was accepted in ACM Multimedia 2024.
  • 2024-07: One paper to appear in ECCV 2024 .
  • 2024-04: One first author paper was accepted in ICME 2024 (Oral).
  • 2024-01: One first author paper was accepted in Machine Intelligence Research.
  • 2024-01: One paper to appear in ICLR 2024.
  • 2023-12: One first author paper was accepted in AAAI 2024.
  • 2023-05: One first author paper was accepted in IEEE Trans. Neural Networks Learn. Syst.
  • 2023-04: One paper to appear in ICML 2023.
  • 2023-04: One paper to appear in CVPRW 2022.

Education

Harbin Institute of Technology
Ph.D. student, 2020 ~ present.

Soochow University
B.Eng., Major in Computer Science, Sep 2016 - Jul 2020.

Publications

IEEE Transactions on Image Processing
Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach
Gang Wu, Junjun Jiang, Junpeng Jiang, Xianming Liu
[Code][paper]
Under Review
Debiased All-in-one Image Restoration with Task Uncertainty Regularization
Gang Wu, Junjun Jiang, Yijun Wang, Kui Jiang, Xianming Liu
[Code] and [Paper] are coming soon.
ACM MM 24
Harmony in Diversity: Improving All-in-One Image Restoration via Multi-Task Collaboration
Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu
[Code] [Paper]
ICME, 2024 (Oral)
Exploiting Self-Supervised Constraints in Image Super-Resolution
Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu
[Code][Arxiv]
AAAI, 2024
Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu
[Project][Code][Arxiv]

🔥 The extended journal version is under review.

Machine Intelligence Research, 2024
Fully 1×1 Convolutional Network for Lightweight Image Super-Resolution
Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu
[Code][Arxiv]
IEEE Trans. Neural Networks Learn. Syst., 2023
A Practical Contrastive Learning Framework for Single-Image Super-Resolution
Gang Wu, Junjun Jiang, Junpeng Jiang, Xianming Liu
[Code][Arxiv]
ECCV 2024
Improving Domain Generalization in Self-Supervised Monocular Depth Estimation via Stabilized Adversarial Training
Yuanqi Yao, Gang Wu, Kui Jiang, Siao Liu, Jian Kuai, Xianming Liu, and Junjun Jiang

ICLR 2024
Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs
Xiong Zhou, Xianming Liu, Feilong Zhang, Gang Wu, Deming Zhai, Junjun Jiang, Xiangyang Ji
[Code][Paper]
ICML 2023
No one idles: Efficient heterogeneous federated learning with parallel edge and server computation
Feilong Zhang, Xianming Liu, Shiyi Lin, Gang Wu, Xiong Zhou, Junjun Jiang, Xiangyang Ji Junjun Jiang, Xianming Liu
[Code] [Paper]
Arxiv
Incorporating transformer designs into convolutions for lightweight image super-resolution
Gang Wu, Junjun Jiang, Yuanchao Bai, Xianming Liu
[Code][Arxiv]

Experience

MEGVII
2022.4 ~ 2022.10. Research Intern.

Academic Service & Awards

Competition Awards

ICRA 2023 RoboDepth Challenge, 3rd place in Track 1 and Innovative Prize in Track 2.
NTIRE 2022 Image Inpainting Challenge, 2nd place in Track 1.

Reviewer

The International Conference on Learning Representations (ICLR)
The International Joint Conference on Artificial Intelligence (IJCAI)
The International Conference on Machine Learning (ICML)
ACM Multimedia (ACM MM)
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
IEEE International Conference on Multimedia and Expo (ICME)
IEEE Transactions on Neural Networks and Learning Systems
IEEE Transactions on Circuits and Systems for Video Technology
IEEE Transactions on Multimedia
IEEE Transactions on Image Processing
Information Fusion