# AFFACT - Alignment-Free Facial Attribute Classification Technique

arXiv: https://arxiv.org/abs/1611.06158 · HTML: https://mlsanity.com/paper/1611.06158/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2016.

## Built on by (most cited first, 4 of 4)

- [Consistency and Accuracy of CelebA Attribute Values](https://mlsanity.com/paper/2210.07356/) (2022)
- [CAT: Controllable Attribute Translation for Fair Facial Attribute Classification](https://mlsanity.com/paper/2209.06850/) (2022)
- [LogicNet: A Logical Consistency Embedded Face Attribute Learning Network](https://mlsanity.com/paper/2311.11208/) (2023)
- [Biased Binary Attribute Classifiers Ignore the Majority Classes](https://mlsanity.com/paper/2403.14435/) (2024)

## Abstract (arXiv)

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%.