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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Zhen, Tan, Lei, Shen, Yunhang, Cai, Chengmao, Sun, Xing, Dai, Pingyang, Cao, Liujuan, Ji, Rongrong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912654676721664
author Sun, Zhen
Tan, Lei
Shen, Yunhang
Cai, Chengmao
Sun, Xing
Dai, Pingyang
Cao, Liujuan
Ji, Rongrong
author_facet Sun, Zhen
Tan, Lei
Shen, Yunhang
Cai, Chengmao
Sun, Xing
Dai, Pingyang
Cao, Liujuan
Ji, Rongrong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15595
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification
Sun, Zhen
Tan, Lei
Shen, Yunhang
Cai, Chengmao
Sun, Xing
Dai, Pingyang
Cao, Liujuan
Ji, Rongrong
Computer Vision and Pattern Recognition
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.
title FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.15595