Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learning

TL;DR

Debiased-CAM is a novel method that improves the faithfulness of visual explanations in machine learning models by mitigating systematic biases, leading to better trust and performance.

Contribution

It introduces a multi-input, multi-task training approach that enhances explanation faithfulness across various bias types and levels.

Findings

Enhanced prediction accuracy in biased images

Generated highly faithful explanations similar to unbiased images

Improved user trust and task performance with debiased explanations

Abstract

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.