A Deep Cascade Network for Unaligned Face Attribute Classification
This addresses the problem of accurate face attribute recognition in unaligned images for computer vision applications, representing a strong specific gain.
The paper tackles face attribute classification without alignment by proposing a cascade network that learns to localize attribute-specific face regions and performs classification, achieving a 30.9% reduction in error on the unaligned CelebA dataset.
Humans focus attention on different face regions when recognizing face attributes. Most existing face attribute classification methods use the whole image as input. Moreover, some of these methods rely on fiducial landmarks to provide defined face parts. In this paper, we propose a cascade network that simultaneously learns to localize face regions specific to attributes and performs attribute classification without alignment. First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) specific to attributes. Then multiple part-based networks and a whole-image-based network are separately constructed and combined together by the region switch layer and attribute relation layer for final attribute classification. A multi-net learning method and hint-based model compression is further proposed to get an effective localization model and a compact classification model, respectively. Our approach achieves significantly better performance than state-of-the-art methods on unaligned CelebA dataset, reducing the classification error by 30.9%.