Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuning

About

Recent advancements in adapting vision-language pre-training models like CLIP for person re-identification (ReID) tasks often rely on complex adapter design or modality-specific tuning while neglecting cross-modal interaction, leading to high computational costs or suboptimal alignment. To address these limitations, we propose a simple yet effective framework named Selective Cross-modal Prompt Tuning (SCING) that enhances cross-modal alignment and robustness against real-world perturbations. Our method introduces two key innovations: Firstly, we proposed Selective Visual Prompt Fusion (SVIP), a lightweight module that dynamically injects discriminative visual features into text prompts via a cross-modal gating mechanism. Moreover, the proposed Perturbation-Driven Consistency Alignment (PDCA) is a dual-path training strategy that enforces invariant feature alignment under random image perturbations by regularizing consistency between original and augmented cross-modal embeddings. Extensive experiments are conducted on several popular benchmarks covering Market1501, DukeMTMC-ReID, Occluded-Duke, Occluded-REID, and P-DukeMTMC, which demonstrate the impressive performance of the proposed method. Notably, our framework eliminates heavy adapters while maintaining efficient inference, achieving an optimal trade-off between performance and computational overhead. The code will be released upon acceptance.

Yunfei Xie, Yuxuan Cheng, Juncheng Wu, Haoyu Zhang, Yuyin Zhou, Shoudong Han• 2025

Related benchmarks

TaskDatasetResultRank
Person Re-IdentificationDukeMTMC
R1 Accuracy91.3
206
Person Re-IdentificationMarket1501
mAP0.91
143
Person Re-IdentificationOccluded-Duke
mAP0.634
131
Person Re-IdentificationOccluded-reID
R-193.8
104
Person Re-IdentificationP-DukeMTMC
Rank-1 Acc93.7
23
Person Re-IdentificationOccluded-Market
Rank-1 Accuracy80.3
17
Showing 6 of 6 rows

Other info

Follow for update