论文标题
视觉偏见的认知不确定性加权损失
Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation
论文作者
论文摘要
深度神经网络非常容易受到视觉数据中学习偏见的影响。尽管已经提出了各种方法来减轻这种偏见，但大多数人都需要明确了解培训数据中存在的偏见以减轻。我们争辩说，探索完全不知道任何偏见但能够识别和减轻它们的方法的方法的相关性。此外，我们建议使用具有预测性不确定性加权损失函数的贝叶斯神经网络，以动态识别单个训练样本中的潜在偏见，并在训练过程中加重它们。我们发现样品之间存在偏见和较高认知不确定性的样本之间的正相关。最后，我们表明该方法具有减轻偏置基准数据集和现实面部检测问题上的视觉偏见的潜力，我们考虑了我们方法的优点和弱点。
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.
