Localization Guided Learning for Pedestrian Attribute Recognition
This work addresses a key bottleneck in pedestrian attribute recognition for surveillance and scene analysis, offering an incremental improvement over existing methods.
The paper tackles the problem of localizing attribute-specific areas in pedestrian attribute recognition by proposing a Localization Guided Network that assigns attribute-specific weights to local features based on affinity with proposals. The result shows state-of-the-art performance on PA-100K and RAP benchmarks, surpassing previous methods in all five metrics.
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.