Explainability-aided Domain Generalization for Image Classification

TL;DR

This paper introduces explainability-guided algorithms that enhance domain generalization in image classification, achieving state-of-the-art performance while providing better insights into model decisions.

Contribution

It proposes novel algorithms like DivCAM, ProDrop, and D-Transformers that integrate explainability techniques with domain generalization, improving robustness and interpretability.

Findings

Achieves state-of-the-art domain generalization performance.

Provides a framework for explainability in deep learning models.

Enhances model robustness through explainability-guided training.

Abstract

Traditionally, for most machine learning settings, gaining some degree of explainability that tries to give users more insights into how and why the network arrives at its predictions, restricts the underlying model and hinders performance to a certain degree. For example, decision trees are thought of as being more explainable than deep neural networks but they lack performance on visual tasks. In this work, we empirically demonstrate that applying methods and architectures from the explainability literature can, in fact, achieve state-of-the-art performance for the challenging task of domain generalization while offering a framework for more insights into the prediction and training process. For that, we develop a set of novel algorithms including DivCAM, an approach where the network receives guidance during training via gradient based class activation maps to focus on a diverse set of discriminative features, as well as ProDrop and D-Transformers which apply prototypical networks to the domain generalization task, either with self-challenging or attention alignment. Since these methods offer competitive performance on top of explainability, we argue that the proposed methods can be used as a tool to improve the robustness of deep neural network architectures.