Localization Guided Learning for Pedestrian Attribute Recognition

TL;DR

This paper introduces a Localization Guided Network for pedestrian attribute recognition that automatically learns attribute-specific local features, improving accuracy over previous methods by effectively localizing attribute regions.

Contribution

The proposed model automatically learns and emphasizes attribute-specific local features using localization guidance, outperforming existing methods on benchmark datasets.

Findings

Achieved state-of-the-art results on PA-100K and RAP datasets.

Outperformed previous methods in all five evaluation metrics.

Effectively localized attribute regions without additional pose or viewpoint info.

Abstract

Pedestrian attribute recognition has attracted many attentions due to its wide applications in scene understanding and person analysis from surveillance videos. Existing methods try to use additional pose, part or viewpoint information to complement the global feature representation for attribute classification. However, these methods face difficulties in localizing the areas corresponding to different attributes. To address this problem, we propose a novel Localization Guided Network which assigns attribute-specific weights to local features based on the affinity between proposals pre-extracted proposals and attribute locations. The advantage of our model is that our local features are learned automatically for each attribute and emphasized by the interaction with global features. We demonstrate the effectiveness of our Localization Guided Network on two pedestrian attribute benchmarks (PA-100K and RAP). Our result surpasses the previous state-of-the-art in all five metrics on both datasets.