用视觉语言模型提升行人属性识别准确率，解决类别不平衡问题。
VLM-PAR: A Vision Language Model for Pedestrian Attribute Recognition
- 通过跨注意力融合优化视觉特征，对齐图像与提示嵌入
- 在PA100K上达到新最好成绩，其他数据集均显著提效
- 适合关注行人分析、跨模态学习的研究者
行人属性识别（PAR）旨在从行人图像中预测细粒度属性，如衣着颜色、性别和配饰，但面临严重类别不平衡、属性间复杂依赖关系以及域偏移等挑战。我们提出VLM-PAR，一种基于冻结的SigLIP 2多语言编码器的模块化视觉语言框架。通过先对图像与提示嵌入进行对齐，再利用紧凑的交叉注意力融合精炼视觉特征，VLM-PAR在高度不平衡的PA100K基准上实现显著准确率提升，创下新的最先进性能；同时在PETA和Market-1501基准上也取得显著的平均准确率增益。结果表明，将大规模视觉语言预训练与针对性的跨模态精炼相结合，可有效应对PAR中的类别不平衡与泛化难题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。