Saved in:
Bibliographic Details
Main Authors: Li, He, Ye, Mang, Zhang, Ming, Du, Bo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.04741
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910438433751040
author Li, He
Ye, Mang
Zhang, Ming
Du, Bo
author_facet Li, He
Ye, Mang
Zhang, Ming
Du, Bo
contents In Re-identification (ReID), recent advancements yield noteworthy progress in both unimodal and cross-modal retrieval tasks. However, the challenge persists in developing a unified framework that could effectively handle varying multimodal data, including RGB, infrared, sketches, and textual information. Additionally, the emergence of large-scale models shows promising performance in various vision tasks but the foundation model in ReID is still blank. In response to these challenges, a novel multimodal learning paradigm for ReID is introduced, referred to as All-in-One (AIO), which harnesses a frozen pre-trained big model as an encoder, enabling effective multimodal retrieval without additional fine-tuning. The diverse multimodal data in AIO are seamlessly tokenized into a unified space, allowing the modality-shared frozen encoder to extract identity-consistent features comprehensively across all modalities. Furthermore, a meticulously crafted ensemble of cross-modality heads is designed to guide the learning trajectory. AIO is the \textbf{first} framework to perform all-in-one ReID, encompassing four commonly used modalities. Experiments on cross-modal and multimodal ReID reveal that AIO not only adeptly handles various modal data but also excels in challenging contexts, showcasing exceptional performance in zero-shot and domain generalization scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04741
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle All in One Framework for Multimodal Re-identification in the Wild
Li, He
Ye, Mang
Zhang, Ming
Du, Bo
Computer Vision and Pattern Recognition
In Re-identification (ReID), recent advancements yield noteworthy progress in both unimodal and cross-modal retrieval tasks. However, the challenge persists in developing a unified framework that could effectively handle varying multimodal data, including RGB, infrared, sketches, and textual information. Additionally, the emergence of large-scale models shows promising performance in various vision tasks but the foundation model in ReID is still blank. In response to these challenges, a novel multimodal learning paradigm for ReID is introduced, referred to as All-in-One (AIO), which harnesses a frozen pre-trained big model as an encoder, enabling effective multimodal retrieval without additional fine-tuning. The diverse multimodal data in AIO are seamlessly tokenized into a unified space, allowing the modality-shared frozen encoder to extract identity-consistent features comprehensively across all modalities. Furthermore, a meticulously crafted ensemble of cross-modality heads is designed to guide the learning trajectory. AIO is the \textbf{first} framework to perform all-in-one ReID, encompassing four commonly used modalities. Experiments on cross-modal and multimodal ReID reveal that AIO not only adeptly handles various modal data but also excels in challenging contexts, showcasing exceptional performance in zero-shot and domain generalization scenarios.
title All in One Framework for Multimodal Re-identification in the Wild
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.04741