Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learning
This addresses the issue of misleading AI explanations for users in applications with biased data, offering a method to improve trust and performance, though it is incremental as it builds on existing CAM techniques.
The paper tackled the problem of distorted saliency maps in AI explanations due to systematic biases in images, presenting Debiased-CAM to recover faithful visual explanations. The result showed enhanced prediction accuracy and highly faithful explanations in simulations, with user studies indicating improved task performance, perceived truthfulness, and helpfulness.
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic error (bias). Furthermore, the distortions persist despite model fine-tuning on images biased by different factors (blur, color temperature, day/night). We present Debiased-CAM to recover explanation faithfulness across various bias types and levels by training a multi-input, multi-task model with auxiliary tasks for explanation and bias level predictions. In simulation studies, the approach not only enhanced prediction accuracy, but also generated highly faithful explanations about these predictions as if the images were unbiased. In user studies, debiased explanations improved user task performance, perceived truthfulness and perceived helpfulness. Debiased training can provide a versatile platform for robust performance and explanation faithfulness for a wide range of applications with data biases.