Distance-Aware eXplanation Based Learning

TL;DR

This paper introduces a distance-aware explanation loss for eXplanation Based Learning, improving model focus on relevant image regions and proposing a new interpretability metric for visual explanations.

Contribution

It presents a novel distance-aware explanation loss for XBL and a new interpretability metric, enhancing training and evaluation of visual model explanations.

Findings

Improved focus on important image regions in classification tasks.

Proposed interpretability metric outperforms existing metrics.

Effective on three image classification datasets.

Abstract

eXplanation Based Learning (XBL) is an interactive learning approach that provides a transparent method of training deep learning models by interacting with their explanations. XBL augments loss functions to penalize a model based on deviation of its explanations from user annotation of image features. The literature on XBL mostly depends on the intersection of visual model explanations and image feature annotations. We present a method to add a distance-aware explanation loss to categorical losses that trains a learner to focus on important regions of a training dataset. Distance is an appropriate approach for calculating explanation loss since visual model explanations such as Gradient-weighted Class Activation Mapping (Grad-CAMs) are not strictly bounded as annotations and their intersections may not provide complete information on the deviation of a model's focus from relevant image regions. In addition to assessing our model using existing metrics, we propose an interpretability metric for evaluating visual feature-attribution based model explanations that is more informative of the model's performance than existing metrics. We demonstrate performance of our proposed method on three image classification tasks.