Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancement

arXiv:2404.11819v1 Announce Type: new
Abstract: We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals themselves are often generated from biased generative models, which can introduce additional biases or spurious correlations. To address this issue, we propose using adversarial images, that is images that deceive a deep neural network but not humans, as counterfactuals for fair model …

abstract accuracy adversarial adversarial examples analyze arxiv bias biases computer computer vision counterfactual cs.cv dnn examples fine-tuning generated generative generative models novel type vision vision models