Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Face DetectionSimilar Papers 제목 키워드 기반
Why Machine Learning Models Fail to Fully Capture Epistemic Uncertainty
In recent years various supervised learning methods that disentangle aleatoric and epistemic uncertainty based on second-order distributions have been proposed. We argue that these methods fail to capture critical compon…
Uncertainty QuantificationDense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty. In current aleatoric uncertainty estimation frameworks, it is …
Attributeobject-detectionObject DetectionCertainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness
The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to v…
Image CaptioningQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient knowledge about the model, can be reduced…
Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning
The overall predictive uncertainty of a trained predictor can be decomposed into separate contributions due to epistemic and aleatoric uncertainty. Under a Bayesian formulation, assuming a well-specified model, the two c…
Meta-Learning