RES: A Robust Framework for Guiding Visual Explanation

TL;DR

This paper introduces RES, a robust framework that improves the quality of visual explanations in deep neural networks by addressing annotation inaccuracies and inconsistencies, leading to better interpretability and model performance.

Contribution

The paper proposes a novel, theoretically justified framework for guiding visual explanations, effectively handling annotation challenges and enhancing explanation quality in DNNs.

Findings

Improves explanation reasonability and accuracy

Enhances DNN performance through better explanations

Addresses annotation boundary and distribution issues

Abstract

Despite the fast progress of explanation techniques in modern Deep Neural Networks (DNNs) where the main focus is handling "how to generate the explanations", advanced research questions that examine the quality of the explanation itself (e.g., "whether the explanations are accurate") and improve the explanation quality (e.g., "how to adjust the model to generate more accurate explanations when explanations are inaccurate") are still relatively under-explored. To guide the model toward better explanations, techniques in explanation supervision - which add supervision signals on the model explanation - have started to show promising effects on improving both the generalizability as and intrinsic interpretability of Deep Neural Networks. However, the research on supervising explanations, especially in vision-based applications represented through saliency maps, is in its early stage due to several inherent challenges: 1) inaccuracy of the human explanation annotation boundary, 2) incompleteness of the human explanation annotation region, and 3) inconsistency of the data distribution between human annotation and model explanation maps. To address the challenges, we propose a generic RES framework for guiding visual explanation by developing a novel objective that handles inaccurate boundary, incomplete region, and inconsistent distribution of human annotations, with a theoretical justification on model generalizability. Extensive experiments on two real-world image datasets demonstrate the effectiveness of the proposed framework on enhancing both the reasonability of the explanation and the performance of the backbone DNNs model.