Chang-Bin Zhang 张长彬 Ph.D. Candidate The University of Hong Kong Email: zhangchbin@gmail.com [Curriculum Vitae] Google Scholar

I'm currently a third-year Ph.D. candidate working with Dr. Yujie Zhong and Prof. Kai Han at The University of Hong Kong (HKU) . Before that, I spent wonderful years at Nankai University (NKU), supervised by Prof. Ming-Ming Cheng and received my M.Eng degree in Computer Science.

My research interests lie in object detection and multi-modal large language models. I'm fortunate to work with exceptional collaborators, from whom I've learned a great deal.

I am actively seeking internship and collaboration opportunities related to MLLM. Feel free to contact me!

News

[04/2025] v-CLR was selected as a highlight paper in CVPR 2025
[03/2025] Two papers (Mr. DETR, v-CLR) are accepted to CVPR 2025
[01/2024] I have passed [STAT 6008] Advanced Statistical Inference
[01/2024] I have passed [STAT 6009] Research Methods in Statistics (Advanced Probability Theory and Measure Theory)
[04/2023] One paper (EWF) is accepted to CVPR 2023
[03/2022] One paper (RCIL) is accepted to CVPR 2022
[07/2021] One paper is accepted to ICCV 2021
[06/2021] Two papers (LayerCAM, OLS) are accepted to IEEE TIP 2021
[05/2021] One paper is accepted to IEEE TPAMI 2021

Publications

• Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts
  Chang-Bin Zhang, Yujie Zhong and Kai Han
  Under Review, 2025
  [arXiv] [code] [project page] [HuggingFace Demo]
  A powerful, SOTA object detection model, an enhanced version of Mr. DETR
  Support object detection, instance segmentation and panoptic segmentation

• What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?
  Jinhong Ni, Chang-Bin Zhang, Qiang Zhang and Jing Zhang
  ICCV, 2025
  [arXiv] [code] [HuggingFace Demo]

• Mr. DETR: Instructive Multi-Route Training for Detection Transformers
  Chang-Bin Zhang, Yujie Zhong and Kai Han
  CVPR, 2025
  [arXiv] [code] [project page] [HuggingFace Demo]
  [04/25] Rank #1 in the Leaderboard of COCO 2017 val

• v-CLR: View-Consistent Learning for Open-World Instance Segmentation
  Chang-Bin Zhang, Jinhong Ni, Yujie Zhong and Kai Han
  CVPR, 2025, Highlight
  [arXiv] [code] [project page] [HuggingFace Demo]

• Endpoints Weight Fusion for Class Incremental Semantic Segmentation
  Jia-Wen Xiao*, Chang-Bin Zhang*, Jiekang Feng, Xialei Liu, Joost van de Weijer and Ming-Ming Cheng
  CVPR, 2023
  [IEEE/CVF] [code]

• Representation Compensation Networks for Continual Semantic Segmentation
  Chang-Bin Zhang*, Jia-Wen Xiao*, Xialei Liu, Yingcong Chen and Ming-Ming Cheng
  CVPR, 2022
  [IEEE/CVF] [arXiv] [中译版] [code]

• Delving Deep into Label Smoothing
  Chang-Bin Zhang*, Peng-Tao Jiang*, Qibin Hou, Yunchao Wei, Qi Han, Zhen Li and Ming-Ming Cheng
  IEEE Transactions on Image Processing (IEEE TIP), 2021
  [IEEE Explore] [arXiv] [中译版] [code]

• LayerCAM: Exploring Hierarchical Class Activation Maps For Localization
  Peng-Tao Jiang*, Chang-Bin Zhang*, Qibin Hou, Ming-Ming Cheng and Yunchao Wei
  IEEE Transactions on Image Processing (IEEE TIP), 2021
  [IEEE Explore] [中译版] [code] [ESI Highly Cited Paper (1%)]
  The FIRST tool to extract class activation maps from ANY layer in networks

• Personalized Image Semantic Segmentation
  Yu Zhang, Chang-Bin Zhang, Peng-Tao Jiang, Ming-Ming Cheng and Mao Feng
  ICCV, 2021
  [IEEE/CVF] [arXiv] [中译版] [code]

• Deep Hough Transform for Semantic Line Detection
  Kai Zhao*, Qi Han*, Chang-Bin Zhang, Jun Xu, and Ming-Ming Cheng
  IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2021
  [IEEE Explore] [arXiv] [中译版] [code] [ESI Highly Cited Paper (1%)]

Experience

• SAIC Motor Autonomous, Engineer, 2022.07~2023.01, Shanghai, working closely with Dr. Peixuan Li
  

• NIO Autonomous, Internship, 2022.01~2022.04, Beijing
  

• DJI Autonomous, Internship, 2021.06~2021.08, Shenzhen