Contrastive Explanations in Neural Networks

TL;DR

This paper introduces a formal framework for contrastive visual explanations in neural networks, enhancing interpretability by answering specific 'Why P rather than Q' questions using a plug-in approach with Grad-CAM.

Contribution

It formalizes contrastive explanations for neural networks and proposes a methodology to extract and incorporate contrasts into existing explanation techniques.

Findings

Effective contrastive explanations improve interpretability.

Applicable across various domains like recognition and seismic analysis.

Enhances understanding of neural network decisions.

Abstract

Visual explanations are logical arguments based on visual features that justify the predictions made by neural networks. Current modes of visual explanations answer questions of the form $`Why \text{ } P?'$. These $Why$ questions operate under broad contexts thereby providing answers that are irrelevant in some cases. We propose to constrain these $Why$ questions based on some context $Q$ so that our explanations answer contrastive questions of the form $`Why \text{ } P, \text{} rather \text{ } than \text{ } Q?'$. In this paper, we formalize the structure of contrastive visual explanations for neural networks. We define contrast based on neural networks and propose a methodology to extract defined contrasts. We then use the extracted contrasts as a plug-in on top of existing $`Why \text{ } P?'$ techniques, specifically Grad-CAM. We demonstrate their value in analyzing both networks and data in applications of large-scale recognition, fine-grained recognition, subsurface seismic analysis, and image quality assessment.