Multi-Modal Object Re-identification via Sparse Mixture-of-Experts

We present MFRNet, a novel network for multimodal object re-identification that integrates multi-modal data features to effectively retrieve specific objects across different modalities. Current methods suffer from two principal limitations: (1) insufficient interaction between pixellevel semantic features across modalities, and (2) difficulty in balancing modality-shared and modality-specific features within a unified architecture. To address these challenges, our network introduces two core components. First, the Feature Fusion Module (FFM) enables finegrained pixel-level feature generation and flexible cross-modal interaction. Second, the Feature Representation Module (FRM) efficiently extracts and combines modality-specific and modality-shared features, achieving strong discriminative ability with minimal parameter overhead. Extensive experiments on three challenging public datasets (RGBNT201, RGBNT100, and MSVR310) demonstrate the superiority of our approach in terms of both accuracy and efficiency, with 8.4% mAP and 6.9% accuracy improved in RGBNT201 with negligible additional parameters. The code is available at https: //github.com/stone96123/MFRNet .