English

AFFACT - Alignment-Free Facial Attribute Classification Technique

Computer Vision and Pattern Recognition 2017-08-08 v2

Abstract

Facial attributes are soft-biometrics that allow limiting the search space, e.g., by rejecting identities with non-matching facial characteristics such as nose sizes or eyebrow shapes. In this paper, we investigate how the latest versions of deep convolutional neural networks, ResNets, perform on the facial attribute classification task. We test two loss functions: the sigmoid cross-entropy loss and the Euclidean loss, and find that for classification performance there is little difference between these two. Using an ensemble of three ResNets, we obtain the new state-of-the-art facial attribute classification error of 8.00% on the aligned images of the CelebA dataset. More significantly, we introduce the Alignment-Free Facial Attribute Classification Technique (AFFACT), a data augmentation technique that allows a network to classify facial attributes without requiring alignment beyond detected face bounding boxes. To our best knowledge, we are the first to report similar accuracy when using only the detected bounding boxes -- rather than requiring alignment based on automatically detected facial landmarks -- and who can improve classification accuracy with rotating and scaling test images. We show that this approach outperforms the CelebA baseline on unaligned images with a relative improvement of 36.8%.

Keywords

Cite

@article{arxiv.1611.06158,
  title  = {AFFACT - Alignment-Free Facial Attribute Classification Technique},
  author = {Manuel Günther and Andras Rozsa and Terrance E. Boult},
  journal= {arXiv preprint arXiv:1611.06158},
  year   = {2017}
}

Comments

This is a pre-print of the original paper accepted for oral presentation at the International Joint Conference on Biometrics (IJCB) 2017

R2 v1 2026-06-22T16:57:15.065Z