Gengwei Zhang (David)

Ph.D. student
Faculty of Engineering & IT
University of Technology Sydney
Email: zgwdavid AT gmail.com (prefered); gengwei.zhang AT student.uts.edu.au

About Me

I am a Ph.D. student in the Faculty of Engineering and Information Technology at the University of Technology Sydney (UTS), supervised by Prof. Yunchao Wei and Prof. Ling Chen . I received my bachelor’s degree in School of Data and Computer Science (currently School of Computer Science and Engineering) from Sun Yat-Sen University (SYSU). Before UTS, I spent a wonderful year working with Prof. Xiaodan Liang at SYSU as a research assistant.
My current research interests are in Computer Vision and improving vision models with advanced Machine Learning algorithms, such as Automated Machine Learning, Few-shot Learning and Continual Learning. Specifically, I have recently worked in:

• Computer Vision: Object detection, Segmentation and Human pose estimation
• Machine Learning: Self-supervised pre-training, Continual learning, Few-shot learning, Weakly-supervised learning and Automated machine learning.

News

[2024.08] A substantial improvement of our SLCA is available: “[SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training]”. Check it out here. The code is also available.
[2023.07] Our paper “SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model” has been accepted by ICCV 2023, and the code is available here.
[2022.12] Our paper “Mask Matching Transformer for Few-Shot Segmentation” has been accepted by NeurIPS 2022, and the code is available here.
[2021.12] Our paper “Few-Shot Segmentation via Cycle-Consistent Transformer” has been accepted by NeurIPS 2021, and the code is available here.

Publications

Please refer to my Google scholar for a full list of my publications and here are some selective publications.

Continual Learning (Image Classification)

• Gengwei Zhang*, Liyuan Wang*, Guoliang Kang, Ling Chen, and Yunchao Wei.
  “SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model.”
  International Conference on Computer Vision (ICCV), 2023.

Few-shot Learning + Segmentation

• Siyu Jiao, Gengwei Zhang, Shant Navasardyan, Ling Chen, Yao Zhao, Yunchao Wei, Humphrey Shi.
  “Mask Matching Transformer for Few-Shot Segmentation.”
  Conference on Neural Information Processing Systems (NeurIPS), 2022.

• Gengwei Zhang, Guoliang Kang, Yi Yang, Yunchao Wei.
  ”Few-Shot Segmentation via Cycle-Consistent Transformer.”
  Conference on Neural Information Processing Systems (NeurIPS), 2021

AutoML + Segmentation

• Gengwei Zhang, Yiming Gao, Hang Xu, Hao Zhang, Zhenguo Li, Xiaodan Liang.
  ”Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation.”
  Association for the Advancement of Artificial Intelligence (AAAI), 2021.

• Yangxin Wu, Gengwei Zhang, Hang Xu, Liang, Xiaodan and Lin, Liang.
  ”Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation.”
  Conference on Neural Information Processing Systems (NeurIPS), 2020

AutoML + Detection

• Peidong Liu*, Gengwei Zhang*, Bochao Wang, Hang Xu, Xiaodan Liang, Yong Jiang, Zhenguo Li.
  ”Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search.” International Conference on Learning Representations (ICLR), 2021.

Continul Learning + Detection

• Binbin Yang, Xinchi Deng, Han Shi, Changlin Li, Gengwei Zhang, Hang Xu, Shen Zhao, Liang Lin, Xiaodan Liang
  ”Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism.”
  Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Graph Reasoning + Segmentation

• Yangxin Wu*, Gengwei Zhang*, Yiming Gao, Xiajun Deng, Ke Gong, Xiaodan Liang, Liang Lin. ”Bidirectional Graph Reasoning Network for Panoptic Segmentation.” Conference on Computer Vision and Pattern Recognition (CVPR), 2020