Asymmetric Rejection Loss for Fairer Face Recognition

• URL: http://arxiv.org/abs/2002.03276v1
• Date: Sun, 9 Feb 2020 04:01:03 GMT
• Title: Asymmetric Rejection Loss for Fairer Face Recognition
• Authors: Haoyu Qin
• Abstract summary: Research has shown differences in face recognition performance across different ethnic groups due to the racial imbalance in the training datasets. This is actually symptomatic of the under-representation of non-Caucasian ethnic groups in the celebdom from which face datasets are usually gathered. We propose an Asymmetric Rejection Loss, which aims at making full use of unlabeled images of those under-represented groups.
• Score: 1.52292571922932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face recognition performance has seen a tremendous gain in recent years, mostly due to the availability of large-scale face images dataset that can be exploited by deep neural networks to learn powerful face representations. However, recent research has shown differences in face recognition performance across different ethnic groups mostly due to the racial imbalance in the training datasets where Caucasian identities largely dominate other ethnicities. This is actually symptomatic of the under-representation of non-Caucasian ethnic groups in the celebdom from which face datasets are usually gathered, rendering the acquisition of labeled data of the under-represented groups challenging. In this paper, we propose an Asymmetric Rejection Loss, which aims at making full use of unlabeled images of those under-represented groups, to reduce the racial bias of face recognition models. We view each unlabeled image as a unique class, however as we cannot guarantee that two unlabeled samples are from a distinct class we exploit both labeled and unlabeled data in an asymmetric manner in our loss formalism. Extensive experiments show our method's strength in mitigating racial bias, outperforming state-of-the-art semi-supervision methods. Performance on the under-represented ethnicity groups increases while that on the well-represented group is nearly unchanged.

Related papers

• Studying Bias in GANs through the Lens of Race [91.95264864405493]
  We study how the performance and evaluation of generative image models are impacted by the racial composition of their training datasets. Our results show that the racial compositions of generated images successfully preserve that of the training data. However, we observe that truncation, a technique used to generate higher quality images during inference, exacerbates racial imbalances in the data.
  arXiv  Detail & Related papers  (2022-09-06T22:25:56Z)
• A Deep Dive into Dataset Imbalance and Bias in Face Identification [49.210042420757894]
  Media portrayals often center imbalance as the main source of bias in automated face recognition systems. Previous studies of data imbalance in FR have focused exclusively on the face verification setting. This work thoroughly explores the effects of each kind of imbalance possible in face identification, and discuss other factors which may impact bias in this setting.
  arXiv  Detail & Related papers  (2022-03-15T20:23:13Z)
• Measuring Hidden Bias within Face Recognition via Racial Phenotypes [21.74534280021516]
  This study introduces an alternative racial bias analysis methodology via facial phenotype attributes for face recognition. We propose categorical test cases to investigate the individual influence of those attributes on bias within face recognition tasks.
  arXiv  Detail & Related papers  (2021-10-19T10:46:59Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• Learning Fair Face Representation With Progressive Cross Transformer [79.73754444296213]
  We propose a progressive cross transformer (PCT) method for fair face recognition. We show that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance.
  arXiv  Detail & Related papers  (2021-08-11T01:31:14Z)
• An Examination of Fairness of AI Models for Deepfake Detection [5.4852920337961235]
  We evaluate bias present in deepfake datasets and detection models across protected subgroups. Using facial datasets balanced by race and gender, we examine three popular deepfake detectors and find large disparities in predictive performances across races.
  arXiv  Detail & Related papers  (2021-05-02T21:55:04Z)
• Enhancing Facial Data Diversity with Style-based Face Aging [59.984134070735934]
  In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. We propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns. We show that the proposed method outperforms state-of-the-art algorithms for age transfer.
  arXiv  Detail & Related papers  (2020-06-06T21:53:44Z)
• Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation [15.924281804465252]
  We propose a novel adversarial derived data augmentation methodology that aims to enable dataset balance at a per-subject level. Our aim is to automatically construct a synthesised dataset by transforming facial images across varying racial domains. In a side-by-side comparison, we show the positive impact our proposed technique can have on the recognition performance for (racial) minority groups.
  arXiv  Detail & Related papers  (2020-04-19T19:46:32Z)
• Boosting Unconstrained Face Recognition with Auxiliary Unlabeled Data [59.85605718477639]
  We present an approach to use unlabeled faces to learn generalizable face representations. Experimental results on unconstrained datasets show that a small amount of unlabeled data with sufficient diversity can lead to an appreciable gain in recognition performance.
  arXiv  Detail & Related papers  (2020-03-17T20:58:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.