A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving

TL;DR

This paper introduces a lightweight CLIP-based framework called UMM that enhances pedestrian re-identification in autonomous driving by effectively handling uncertain or missing modalities with improved robustness and efficiency.

Contribution

The paper proposes a novel UMM framework that integrates multimodal token mapping, synthetic data augmentation, and cross-modal interaction, leveraging CLIP for efficient multimodal fusion in resource-limited settings.

Findings

UMM achieves high robustness under uncertain modality conditions.

The framework demonstrates strong generalization across different data types.

It offers computational efficiency suitable for real-time autonomous driving applications.

Abstract

Re-Identification (ReID) is a critical technology in intelligent perception systems, especially within autonomous driving, where onboard cameras must identify pedestrians across views and time in real-time to support safe navigation and trajectory prediction. However, the presence of uncertain or missing input modalities--such as RGB, infrared, sketches, or textual descriptions--poses significant challenges to conventional ReID approaches. While large-scale pre-trained models offer strong multimodal semantic modeling capabilities, their computational overhead limits practical deployment in resource-constrained environments. To address these challenges, we propose a lightweight Uncertainty Modal Modeling (UMM) framework, which integrates a multimodal token mapper, synthetic modality augmentation strategy, and cross-modal cue interactive learner. Together, these components enable unified feature representation, mitigate the impact of missing modalities, and extract complementary information across different data types. Additionally, UMM leverages CLIP's vision-language alignment ability to fuse multimodal inputs efficiently without extensive finetuning. Experimental results demonstrate that UMM achieves strong robustness, generalization, and computational efficiency under uncertain modality conditions, offering a scalable and practical solution for pedestrian re-identification in autonomous driving scenarios.