paper-with-me

홈 › Papers

Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention

2023-04-05 · Linzhi Huang, Mei Wang, Jiahao Liang, Weihong Deng, Hongzhi Shi, Dongchao Wen, Yingjie Zhang, Jian Zhao

Although face recognition has made impressive progress in recent years, we ignore the racial bias of the recognition system when we pursue a high level of accuracy. Previous work found that for different races, face recognition networks focus on different facial regions, and the sensitive regions of darker-skinned people are much smaller. Based on this discovery, we propose a new de-bias method based on gradient attention, called Gradient Attention Balance Network (GABN). Specifically, we use the gradient attention map (GAM) of the face recognition network to track the sensitive facial regions and make the GAMs of different races tend to be consistent through adversarial learning. This method mitigates the bias by making the network focus on similar facial regions. In addition, we also use masks to erase the Top-N sensitive facial regions, forcing the network to allocate its attention to a larger facial region. This method expands the sensitive region of darker-skinned people and further reduces the gap between GAM of darker-skinned people and GAM of Caucasians. Extensive experiments show that GABN successfully mitigates racial bias in face recognition and learns more balanced performance for people of different races.

📄 PDF Abstract BibTeX arXiv:2304.02284

Code (0)

등록된 구현이 없습니다.

Tasks

Face Recognition

Methods 이 논문이 사용한 방법론

GAM 설명 없음

Similar Papers 제목 키워드 기반

Class-Specific Branch Attention for Mitigating Gradient Interference under Class Imbalance

2026-06-04 · Arush Singhal, Umang Soni arxiv

Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias. In this work, we identify a complementary optimization-level pathology: inter-class …

Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning

2020-06-01 · CVPR 2020 6 · Mei Wang, Weihong Deng

Racial equality is an important theme of international human rights law, but it has been largely obscured when the overall face recognition accuracy is pursued blindly. More facts indicate racial bias indeed degrades the…

Face RecognitionFairnessQ-Learningreinforcement-learning+2

What Should Be Balanced in a "Balanced" Face Recognition Dataset?

2023-04-17 · Haiyu Wu, Kevin W. Bowyer

The issue of demographic disparities in face recognition accuracy has attracted increasing attention in recent years. Various face image datasets have been proposed as 'fair' or 'balanced' to assess the accuracy of face …

Face Recognition

Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models

2021-08-14 · Puspita Majumdar, Surbhi Mittal, Richa Singh, Mayank Vatsa

Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good r…

Face Recognition

Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks

2024-01-09 · Yufei Guo, Yuanpei Chen, Zecheng Hao, Weihang Peng 외

The Spiking Neural Network (SNN) is a biologically inspired neural network infrastructure that has recently garnered significant attention. It utilizes binary spike activations to transmit information, thereby replacing …