Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Minghui, Wang, Shu, Wang, Xiang, Tang, Jianhua, Fu, Longbin, Zuo, Zhengrong, Sang, Nong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.10985
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908320424525824
author Lin, Minghui
Wang, Shu
Wang, Xiang
Tang, Jianhua
Fu, Longbin
Zuo, Zhengrong
Sang, Nong
author_facet Lin, Minghui
Wang, Shu
Wang, Xiang
Tang, Jianhua
Fu, Longbin
Zuo, Zhengrong
Sang, Nong
contents Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance. However, these methods usually adopt the standard full fine-tuning paradigm, which requires the optimization of considerable backbone parameters, causing extensive computational and storage requirements. In this work, we propose an efficient prompt-tuning framework tailored for multi-modal object re-identification, dubbed DMPT, which freezes the main backbone and only optimizes several newly added decoupled modality-aware parameters. Specifically, we explicitly decouple the visual prompts into modality-specific prompts which leverage prior modality knowledge from a powerful text encoder and modality-independent semantic prompts which extract semantic information from multi-modal inputs, such as visible, near-infrared, and thermal-infrared. Built upon the extracted features, we further design a Prompt Inverse Bind (PromptIBind) strategy that employs bind prompts as a medium to connect the semantic prompt tokens of different modalities and facilitates the exchange of complementary multi-modal information, boosting final re-identification results. Experimental results on multiple common benchmarks demonstrate that our DMPT can achieve competitive results to existing state-of-the-art methods while requiring only 6.5% fine-tuning of the backbone parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10985
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification
Lin, Minghui
Wang, Shu
Wang, Xiang
Tang, Jianhua
Fu, Longbin
Zuo, Zhengrong
Sang, Nong
Computer Vision and Pattern Recognition
Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance. However, these methods usually adopt the standard full fine-tuning paradigm, which requires the optimization of considerable backbone parameters, causing extensive computational and storage requirements. In this work, we propose an efficient prompt-tuning framework tailored for multi-modal object re-identification, dubbed DMPT, which freezes the main backbone and only optimizes several newly added decoupled modality-aware parameters. Specifically, we explicitly decouple the visual prompts into modality-specific prompts which leverage prior modality knowledge from a powerful text encoder and modality-independent semantic prompts which extract semantic information from multi-modal inputs, such as visible, near-infrared, and thermal-infrared. Built upon the extracted features, we further design a Prompt Inverse Bind (PromptIBind) strategy that employs bind prompts as a medium to connect the semantic prompt tokens of different modalities and facilitates the exchange of complementary multi-modal information, boosting final re-identification results. Experimental results on multiple common benchmarks demonstrate that our DMPT can achieve competitive results to existing state-of-the-art methods while requiring only 6.5% fine-tuning of the backbone parameters.
title DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.10985