CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-Identification
Chenyang Yu, Xuehu Liu, Jiawen Zhu, Yuhao Wang, Pingping Zhang, Huchuan Lu
Abstract
Person Re-IDentification (ReID) aims to identify specific persons from non-overlapping cameras. Recently, some works have suggested using large-scale pre-trained vision-language models like CLIP to boost ReID performance. Unfortunately, existing methods still struggle to address two key issues simultaneously: efficiently transferring the knowledge learned from CLIP and comprehensively extracting the context information from images or videos. To address these issues, we introduce CLIMB-ReID, a pioneering hybrid framework that synergizes the impressive power of CLIP with the remarkable computational efficiency of Mamba. Specifically, we first propose a novel Multi-Memory Collaboration (MMC) strategy to transfer CLIP's knowledge in a parameter-free and prompt-free form. Then, we design a Multi-Temporal Mamba (MTM) to capture multi-granular spatiotemporal information in videos. Finally, with Importance-aware Reorder Mamba (IRM), information from various scales is combined to produce robust sequence features. Extensive experiments show that our proposed method outperforms other state-of-the-art methods on both image and video person ReID benchmarks.
BibTeX
@article{Yu_Liu_Zhu_Wang_Zhang_Lu_2025, title={CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-Identification}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/33039}, DOI={10.1609/aaai.v39i9.33039}, abstractNote={Person Re-IDentification (ReID) aims to identify specific persons from non-overlapping cameras. Recently, some works have suggested using large-scale pre-trained vision-language models like CLIP to boost ReID performance. Unfortunately, existing methods still struggle to address two key issues simultaneously: efficiently transferring the knowledge learned from CLIP and comprehensively extracting the context information from images or videos. To address these issues, we introduce CLIMB-ReID, a pioneering hybrid framework that synergizes the impressive power of CLIP with the remarkable computational efficiency of Mamba. Specifically, we first propose a novel Multi-Memory Collaboration (MMC) strategy to transfer CLIP’s knowledge in a parameter-free and prompt-free form. Then, we design a Multi-Temporal Mamba (MTM) to capture multi-granular spatiotemporal information in videos. Finally, with Importance-aware Reorder Mamba (IRM), information from various scales is combined to produce robust sequence features. Extensive experiments show that our proposed method outperforms other state-of-the-art methods on both image and video person ReID benchmarks.}, number={9}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Yu, Chenyang and Liu, Xuehu and Zhu, Jiawen and Wang, Yuhao and Zhang, Pingping and Lu, Huchuan}, year={2025}, month={Apr.}, pages={9589-9597} }