Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation
원문 초록
Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to mitigate. We argue the relevance of exploring methods which are completely ignorant of the presence of any bias, but are capable of identifying and mitigating them. Furthermore, we propose using Bayesian neural networks with a predictive uncertainty-weighted loss function to dynamically identify potential bias in individual training samples and to weight them during training. We find a positive correlation between samples subject to bias and higher epistemic uncertainties. Finally, we show the method has potential to mitigate visual bias on a bias benchmark dataset and on a real-world face detection problem, and we consider the merits and weaknesses of our approach.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Colors Matter: AI-Driven Exploration of Human Feature Colors
Transforming faces into video stories -- VideoFace2.0
Robust AI-Generated Face Detection with Imbalanced Data
FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methods
MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition
Leveraging Content and Context Cues for Low-Light Image Enhancement
토론
이 논문과 연결된 포럼 글이 아직 없습니다.