DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Yuhao, Liu, Yang, Zheng, Aihua, Zhang, Pingping
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912156243460096
author Wang, Yuhao
Liu, Yang
Zheng, Aihua
Zhang, Pingping
author_facet Wang, Yuhao
Liu, Yang
Zheng, Aihua
Zhang, Pingping
contents Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by combining complementary information from multiple modalities. Existing multi-modal object ReID methods primarily focus on the fusion of heterogeneous features. However, they often overlook the dynamic quality changes in multi-modal imaging. In addition, the shared information between different modalities can weaken modality-specific information. To address these issues, we propose a novel feature learning framework called DeMo for multi-modal object ReID, which adaptively balances decoupled features using a mixture of experts. To be specific, we first deploy a Patch-Integrated Feature Extractor (PIFE) to extract multi-granularity and multi-modal features. Then, we introduce a Hierarchical Decoupling Module (HDM) to decouple multi-modal features into non-overlapping forms, preserving the modality uniqueness and increasing the feature diversity. Finally, we propose an Attention-Triggered Mixture of Experts (ATMoE), which replaces traditional gating with dynamic attention weights derived from decoupled features. With these modules, our DeMo can generate more robust multi-modal features. Extensive experiments on three multi-modal object ReID benchmarks fully verify the effectiveness of our methods. The source code is available at https://github.com/924973292/DeMo.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10650
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification
Wang, Yuhao
Liu, Yang
Zheng, Aihua
Zhang, Pingping
Computer Vision and Pattern Recognition
Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by combining complementary information from multiple modalities. Existing multi-modal object ReID methods primarily focus on the fusion of heterogeneous features. However, they often overlook the dynamic quality changes in multi-modal imaging. In addition, the shared information between different modalities can weaken modality-specific information. To address these issues, we propose a novel feature learning framework called DeMo for multi-modal object ReID, which adaptively balances decoupled features using a mixture of experts. To be specific, we first deploy a Patch-Integrated Feature Extractor (PIFE) to extract multi-granularity and multi-modal features. Then, we introduce a Hierarchical Decoupling Module (HDM) to decouple multi-modal features into non-overlapping forms, preserving the modality uniqueness and increasing the feature diversity. Finally, we propose an Attention-Triggered Mixture of Experts (ATMoE), which replaces traditional gating with dynamic attention weights derived from decoupled features. With these modules, our DeMo can generate more robust multi-modal features. Extensive experiments on three multi-modal object ReID benchmarks fully verify the effectiveness of our methods. The source code is available at https://github.com/924973292/DeMo.
title DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.10650