[CVPR 2025] Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation [PDF] [Code] [Demo]

Ziheng Zhang*, Jianyang Gu*, Arpita Chowdhury, Zheda Mai, David Carlyn, Tanya Berger-Wolf, Yu Su, and Wei-Lun Chao.

• Finer-CAM compares the target class with similar classes for more fine-grained and discriminative explanation.
• Finer-CAM can be extended to multi-modal scenarios to provide accurate localization of text concepts.

[CVPR 2025] Prompt-CAM: A Simpler Interpretable Transformer for Fine-Grained Analysis [PDF] [Code]

Arpita Chowdhury, Dipanjyoti Paul, Zheda Mai, Jianyang Gu, Ziheng Zhang, Kazi Sajeed Mehrab, Elizabeth G Campolongo, Daniel Rubenstein, Charles V Stewart, Anuj Karpatne, Tanya Berger-Wolf, Yu Su, and Wei-Lun Chao.

• Prompt-CAM learns class-specific prompts for unique image patches not seen in other classes.
• Prompt-CAM identifies and localizes the traits that distinguish visually similar categories.

[arXiv] Static Segmentation by Tracking: A Frustratingly Label-Efficient Approach to Fine-Grained Segmentation [PDF] [Code]

Zhenyang Feng, Zihe Wang, Saul Ibaven Bueno, Tomasz Frelek, Advikaa Ramesh, Jingyan Bai, Lemeng Wang, Zanming Huang, Jianyang Gu, Jinsu Yoo, Tai-Yu Pan, Arpita Chowdhury, Michelle Ramirez, Elizabeth G. Campolongo, Matthew J. Thompson, Christopher G. Lawrence, Sydne Record, Neil Rosser, Anuj Karpatne, Daniel Rubenstein, Hilmar Lapp, Charles V. Stewart, Tanya Berger-Wolf, Yu Su, and Wei-Lun Chao.

• SST concatenates specimen images into videos and propagates segmentation masks to unlabeled images with only one labeled image.
• SST enables one-shot instance segmentation on images taken in the wild and trait-based image retrieval.

[CVPR 2024] Efficient Dataset Distillation via Minimax Diffusion [PDF] [Code]

Jianyang Gu, Saeed Vahidian, Vyacheslav Kungurtsev, Haonan Wang, Wei Jiang, Yang You and Yiran Chen.

• Minimax Diffusion only requires 1 hour to finish the distillation for a 10-class subset of full-sized ImageNet.
• Minimax Diffusion generates representative and diverse images, yielding state-of-the-art validation performance.

[AAAI 2024] Summarizing Stream Data for Memory-Restricted Online Continual Learning [PDF] [Code]

Jianyang Gu, Kai Wang, Wei Jiang, and Yang You.

• SSD summarizes the informtion flow in online continual learning into informative samples.
• SSD significantly improves the replay effects, especially for circumstances with restricted memory.

[ICCV 2023] DREAM: Efficient Dataset Distillation by Representative Matching [PDF] [Code]

Yanqing Liu*, Jianyang Gu*, Kai Wang, Zheng Zhu, Wei Jiang, and Yang You.

• DREAM aims to improve the training efficiency by only calculating matching metrics with representative samples.
• DREAM only requires less than 20% of original iterations to achieve baseline performance.

[arXiv] Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification [PDF] [Code]

Jianyang Gu, Hao Luo, Kai Wang, Wei Jiang, Yang You, and Jian Zhao.

• CoP learns the color distribution conditioned on the tasks and image contents during the continual learning process.
• CoP provides substantial improvements on anti-forgetting and generalization without storing images of previous tasks.

[CVPR 2023] MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID [PDF] [Code]

Jianyang Gu, Kai Wang, Hao Luo, Chen Chen, Wei Jiang, Yuqiang Fang, Shanghang Zhang, Yang You, and Jian Zhao.

• MSINet searches the optimal interation between multi-scale branches with a twins contrastive mechanism.
• MSINet yeilds better performance on both supervised and unsupervised tasks with limited parameter size.

[IEEE TIFS] Multi-View Evolutionary Training for Unsupervised Domain Adaptive Person Re-Identification [PDF]

Jianyang Gu, Weihua Chen, Hao Luo, Fan Wang, Hao Li, Wei Jiang, and Weijie Mao.

• MET effectively reduces the clustering noise from the dimensions of snapshot quality and temporal consistency.
• MET significantly improves the training robustness by high-quality clustering results, leading to better model performance.