AFFACT - Alignment-Free Facial Attribute Classification Technique
arXiv:1611.06158
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%.
This is a pre-print of the original paper accepted for oral presentation at the International Joint Conference on Biometrics (IJCB) 2017
References in corpus (5)
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- Some Improvements on Deep Convolutional Neural Network Based Image Classification
- Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
- Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data