UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification

TL;DR

UGG-ReID introduces an uncertainty-guided graph model that enhances multi-modal object re-identification by robustly handling noise and effectively fusing heterogeneous data sources, leading to improved accuracy across diverse datasets.

Contribution

The paper presents a novel uncertainty-guided graph framework that models local and sample-level uncertainties to improve robustness and multi-modal fusion in object ReID.

Findings

Achieves superior performance on five multi-modal ReID datasets.

Demonstrates enhanced noise immunity compared to existing methods.

Effectively integrates heterogeneous modalities through uncertainty-guided strategies.

Abstract

Multi-modal object Re-IDentification (ReID) has gained considerable attention with the goal of retrieving specific targets across cameras using heterogeneous visual data sources. At present, multi-modal object ReID faces two core challenges: (1) learning robust features under fine-grained local noise caused by occlusion, frame loss, and other disruptions; and (2) effectively integrating heterogeneous modalities to enhance multi-modal representation. To address the above challenges, we propose a robust approach named Uncertainty-Guided Graph model for multi-modal object ReID (UGG-ReID). UGG-ReID is designed to mitigate noise interference and facilitate effective multi-modal fusion by estimating both local and sample-level aleatoric uncertainty and explicitly modeling their dependencies. Specifically, we first propose the Gaussian patch-graph representation model that leverages uncertainty to quantify fine-grained local cues and capture their structural relationships. This process boosts the expressiveness of modal-specific information, ensuring that the generated embeddings are both more informative and robust. Subsequently, we design an uncertainty-guided mixture of experts strategy that dynamically routes samples to experts exhibiting low uncertainty. This strategy effectively suppresses noise-induced instability, leading to enhanced robustness. Meanwhile, we design an uncertainty-guided routing to strengthen the multi-modal interaction, improving the performance. UGG-ReID is comprehensively evaluated on five representative multi-modal object ReID datasets, encompassing diverse spectral modalities. Experimental results show that the proposed method achieves excellent performance on all datasets and is significantly better than current methods in terms of noise immunity. Our code is available at https://github.com/wanxixi11/UGG-ReID.