FairCal: Fairness Calibration for Face Verification
원문 초록
Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionately and negatively impact minority groups, particularly when used by law enforcement. The majority of bias reduction methods have several drawbacks: they use an end-to-end retraining approach, may not be feasible due to privacy issues, and often reduce accuracy. An alternative approach is post-processing methods that build fairer decision classifiers using the features of pre-trained models, thus avoiding the cost of retraining. However, they still have drawbacks: they reduce accuracy (AGENDA, PASS, FTC), or require retuning for different false positive rates (FSN). In this work, we introduce the Fairness Calibration (FairCal) method, a post-training approach that simultaneously: (i) increases model accuracy (improving the state-of-the-art), (ii) produces fairly-calibrated probabilities, (iii) significantly reduces the gap in the false positive rates, (iv) does not require knowledge of the sensitive attribute, and (v) does not require retraining, training an additional model, or retuning. We apply it to the task of Face Verification, and obtain state-of-the-art results with all the above advantages.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Attributes Shape the Embedding Space of Face Recognition Models
Robustly Improving LLM Fairness in Realistic Settings via Interpretability
Improving Fairness of Large Language Models in Multi-document Summarization
Non-Adaptive Adversarial Face Generation
IndianBailJudgments-1200: A Multi-Attribute Dataset for Legal NLP on Indian Bail Orders
FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.