Generating Visual Explanations

TL;DR

This paper introduces a model that jointly predicts image classes and generates discriminative explanations, improving interpretability of visual recognition by focusing on class-specific image features.

Contribution

A novel model with a reinforcement learning-based loss that generates explanations emphasizing class-discriminative image aspects for better interpretability.

Findings

Generated explanations are more discriminative than existing captioning methods.

Model achieves higher consistency between explanations and image content.

Effective on fine-grained bird species classification dataset.

Abstract

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text; contemporary vision-language models can describe image content but fail to take into account class-discriminative image aspects which justify visual predictions. We propose a new model that focuses on the discriminating properties of the visible object, jointly predicts a class label, and explains why the predicted label is appropriate for the image. We propose a novel loss function based on sampling and reinforcement learning that learns to generate sentences that realize a global sentence property, such as class specificity. Our results on a fine-grained bird species classification dataset show that our model is able to generate explanations which are not only consistent with an image but also more discriminative than descriptions produced by existing captioning methods.