AFFACT - Alignment-Free Facial Attribute Classification Technique
This addresses the problem of facial attribute classification for biometric applications by eliminating the need for precise facial alignment, though it is incremental in combining existing methods with new augmentation.
The paper tackles facial attribute classification by introducing AFFACT, a data augmentation technique that achieves state-of-the-art error of 8.00% on aligned CelebA images and improves accuracy by 36.8% on unaligned images without requiring facial alignment.
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%.