Mdreid: Modality-decoupled Learning For Any-to-any Multi-modal Object Re-identification

Abstract

Real-world object re-identification (ReID) systems often face modality inconsistencies, where query and gallery images come from different sensors (e.g., RGB, NIR, TIR). However, most existing methods assume modality-matched conditions, which limits their robustness and scalability in practical applications. To address this challenge, we propose MDReID, a flexible any-to-any image-level ReID framework designed to operate under both modality-matched and modality-mismatched scenarios. MDReID builds on the insight that modality information can be decomposed into two components: modality-shared features that are predictable and transferable, and modality-specific features that capture unique, modality-dependent characteristics. To effectively leverage this, MDReID introduces two key components: the Modality Decoupling Learning (MDL) and Modality-aware Metric Learning (MML). Specifically, MDL explicitly decomposes modality features into modality-shared and modality-specific representations,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfeng2025mdreid

Related papers

• Flexireid: Adaptive Mixture Of Expert For Multi-modal Person Re-identification (2025)0.00
• All In One Framework For Multimodal Re-identification In The Wild (2024)10.35
• Mix-modality Person Re-identification: A New And Practical Paradigm (2024)6.34
• Bridging The Gap: Multi-level Cross-modality Joint Alignment For Visible-infrared Person Re-identification (2023)11.29
• Implicit Discriminative Knowledge Learning For Visible-infrared Person Re-identification (2024)16.19
• Multi-memory Matching For Unsupervised Visible-infrared Person Re-identification (2024)12.02
• IDMR: Towards Instance-driven Precise Visual Correspondence In Multimodal Retrieval (2025)2.29
• Learning Modal-invariant And Temporal-memory For Video-based Visible-infrared Person Re-identification (2022)14.23