AdaFace: Quality Adaptive Margin for Face Recognition
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 18729-18738
Abstract
Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in Supp.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- IARPA Janus Benchmark-B Face Dataset2017
- AgeDB: The First Manually Collected, In-the-Wild Age Database2017
- SphereFace: Deep Hypersphere Embedding for Face Recognition2017
- Joint Face Detection and Alignment Using Multitask Cascaded Convolutional NetworksIEEE Signal Processing Letters, 2016
- Deep Residual Learning for Image Recognition2016
- Frontal to profile face verification in the wild2016
- Deep Learning Face Attributes in the Wild2015
- No-Reference Image Quality Assessment in the Spatial DomainIEEE Transactions on Image Processing, 2012
- Curriculum learning2009
- Image information and visual qualityIEEE Transactions on Image Processing, 2006