hierarchical feature embedding for attribute recognition

• DOI: 10.48550/arxiv.2005.11576
• Publication Date: 2020-06-01
• Authors: Yiru Wang; Weihao Gan; Jie Yang; Yige Wang; Lin Liu; Jiarou Fan; Wei Wu
• Keywords: FOS: Computer and information sciences; 03 medical and health sciences; 0302 clinical medicine; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc. Most of previous work only consider the attribute-level feature embedding, which might perform poorly in complicated heterogeneous conditions. To address this problem, we propose a hierarchical feature embedding (HFE) framework, which learns a fine-grained feature embedding by combining attribute and ID information. In HFE, we maintain the inter-class and intra-class feature embedding simultaneously. Not only samples with the same attribute but also samples with the same ID are gathered more closely, which could restrict the feature embedding of visually hard samples with regard to attributes and improve the robustness to variant conditions. We establish this hierarchical structure by utilizing HFE loss consisted of attribute-level and ID-level constraints. We also introduce an absolute boundary regularization and a dynamic loss weight as supplementary components to help build up the feature embedding. Experiments show that our method achieves the state-of-the-art results on two pedestrian attribute datasets and a facial attribute dataset.<br/>CVPR 2020<br/>