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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Person Re-Identification | DukeMTMC | R1 Accuracy91.3 | 206 | |
| Person Re-Identification | Market1501 | mAP0.91 | 143 | |
| Person Re-Identification | Occluded-Duke | mAP0.634 | 131 | |
| Person Re-Identification | Occluded-reID | R-193.8 | 104 | |
| Person Re-Identification | P-DukeMTMC | Rank-1 Acc93.7 | 23 | |
| Person Re-Identification | Occluded-Market | Rank-1 Accuracy80.3 | 17 |