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

TL;DR

DeMo introduces a novel framework for multi-modal object ReID that decouples modality-specific features and adaptively balances them using a mixture of experts, leading to more robust multi-modal feature representations.

Contribution

The paper proposes a new feature learning framework with decoupled features and dynamic attention-based mixture of experts for improved multi-modal object ReID.

Findings

Outperforms existing methods on three multi-modal ReID benchmarks.

Effectively preserves modality-specific information through hierarchical decoupling.

Enhances robustness of features via dynamic attention in the mixture of experts.

Abstract

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.