FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification

Zhen Sun, Lei Tan, Yunhang Shen, Chengmao Cai, Xing Sun, Pingyang Dai, Liujuan Cao, Rongrong Ji
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57680-57693, 2025.

Abstract

Multimodal person re-identification (Re-ID) aims to match pedestrian images across different modalities. However, most existing methods focus on limited cross-modal settings and fail to support arbitrary query-retrieval combinations, hindering practical deployment. We propose FlexiReID, a flexible framework that supports seven retrieval modes across four modalities: RGB, infrared, sketches, and text. FlexiReID introduces an adaptive mixture-of-experts (MoE) mechanism to dynamically integrate diverse modality features and a cross-modal query fusion module to enhance multimodal feature extraction. To facilitate comprehensive evaluation, we construct CIRS-PEDES, a unified dataset extending four popular Re-ID datasets to include all four modalities. Extensive experiments demonstrate that FlexiReID achieves state-of-the-art performance and offers strong generalization in complex scenarios.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-sun25q, title = {{F}lexi{R}e{ID}: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification}, author = {Sun, Zhen and Tan, Lei and Shen, Yunhang and Cai, Chengmao and Sun, Xing and Dai, Pingyang and Cao, Liujuan and Ji, Rongrong}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {57680--57693}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/sun25q/sun25q.pdf}, url = {https://proceedings.mlr.press/v267/sun25q.html}, abstract = {Multimodal person re-identification (Re-ID) aims to match pedestrian images across different modalities. However, most existing methods focus on limited cross-modal settings and fail to support arbitrary query-retrieval combinations, hindering practical deployment. We propose FlexiReID, a flexible framework that supports seven retrieval modes across four modalities: RGB, infrared, sketches, and text. FlexiReID introduces an adaptive mixture-of-experts (MoE) mechanism to dynamically integrate diverse modality features and a cross-modal query fusion module to enhance multimodal feature extraction. To facilitate comprehensive evaluation, we construct CIRS-PEDES, a unified dataset extending four popular Re-ID datasets to include all four modalities. Extensive experiments demonstrate that FlexiReID achieves state-of-the-art performance and offers strong generalization in complex scenarios.} }
Endnote
%0 Conference Paper %T FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification %A Zhen Sun %A Lei Tan %A Yunhang Shen %A Chengmao Cai %A Xing Sun %A Pingyang Dai %A Liujuan Cao %A Rongrong Ji %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-sun25q %I PMLR %P 57680--57693 %U https://proceedings.mlr.press/v267/sun25q.html %V 267 %X Multimodal person re-identification (Re-ID) aims to match pedestrian images across different modalities. However, most existing methods focus on limited cross-modal settings and fail to support arbitrary query-retrieval combinations, hindering practical deployment. We propose FlexiReID, a flexible framework that supports seven retrieval modes across four modalities: RGB, infrared, sketches, and text. FlexiReID introduces an adaptive mixture-of-experts (MoE) mechanism to dynamically integrate diverse modality features and a cross-modal query fusion module to enhance multimodal feature extraction. To facilitate comprehensive evaluation, we construct CIRS-PEDES, a unified dataset extending four popular Re-ID datasets to include all four modalities. Extensive experiments demonstrate that FlexiReID achieves state-of-the-art performance and offers strong generalization in complex scenarios.
APA
Sun, Z., Tan, L., Shen, Y., Cai, C., Sun, X., Dai, P., Cao, L. & Ji, R.. (2025). FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:57680-57693 Available from https://proceedings.mlr.press/v267/sun25q.html.

Related Material