A Deep Cascade Network for Unaligned Face Attribute Classification

TL;DR

This paper introduces a cascade deep learning network that localizes face regions and classifies face attributes without needing aligned images, significantly improving accuracy on unaligned datasets.

Contribution

It proposes a novel weakly-supervised face region localization method combined with multi-part and whole-image networks for attribute classification without alignment.

Findings

Achieves 30.9% reduction in classification error on CelebA dataset.

Outperforms state-of-the-art methods on unaligned face attribute classification.

Develops a multi-net learning and hint-based model compression approach.

Abstract

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%.