VLM-PAR: A Vision Language Model for Pedestrian Attribute Recognition
About
Pedestrian Attribute Recognition (PAR) involves predicting fine-grained attributes such as clothing color, gender, and accessories from pedestrian imagery, yet is hindered by severe class imbalance, intricate attribute co-dependencies, and domain shifts. We introduce VLM-PAR, a modular vision-language framework built on frozen SigLIP 2 multilingual encoders. By first aligning image and prompt embeddings via refining visual features through a compact cross-attention fusion, VLM-PAR achieves significant accuracy improvement on the highly imbalanced PA100K benchmark, setting a new state-of-the-art performance, while also delivering significant gains in mean accuracy across PETA and Market-1501 benchmarks. These results underscore the efficacy of integrating large-scale vision-language pretraining with targeted cross-modal refinement to overcome imbalance and generalization challenges in PAR.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Pedestrian Attribute Recognition | PA-100K | mA92.88 | 79 | |
| Pedestrian Attribute Recognition | PETA | mA93.52 | 39 | |
| Pedestrian Attribute Recognition | Market1501 | mA85.38 | 3 |