Exploring Part-Informed Visual-Language Learning for Person Re-Identification
This work improves person re-identification for surveillance and security applications by enhancing fine-grained feature consistency, though it is incremental as it builds on existing visual-language learning frameworks.
The paper tackles the problem of person re-identification by addressing the lack of fine-grained part feature supervision in visual-language learning methods, proposing a part-informed approach that achieves state-of-the-art performance, such as 91.0% Rank-1 and 76.9% mAP on the MSMT17 database.
Recently, visual-language learning (VLL) has shown great potential in enhancing visual-based person re-identification (ReID). Existing VLL-based ReID methods typically focus on image-text feature alignment at the whole-body level, while neglecting supervision on fine-grained part features, thus lacking constraints for local feature semantic consistency. To this end, we propose Part-Informed Visual-language Learning ($π$-VL) to enhance fine-grained visual features with part-informed language supervisions for ReID tasks. Specifically, $π$-VL introduces a human parsing-guided prompt tuning strategy and a hierarchical visual-language alignment paradigm to ensure within-part feature semantic consistency. The former combines both identity labels and human parsing maps to constitute pixel-level text prompts, and the latter fuses multi-scale visual features with a light-weight auxiliary head to perform fine-grained image-text alignment. As a plug-and-play and inference-free solution, our $π$-VL achieves performance comparable to or better than state-of-the-art methods on four commonly used ReID benchmarks. Notably, it reports 91.0% Rank-1 and 76.9% mAP on the challenging MSMT17 database, without bells and whistles.