Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization

TL;DR

This paper introduces ISNet, a method that optimizes Layer-wise Relevance Propagation heatmaps to reduce background bias in deep neural networks, improving their robustness and generalization without extra computational cost.

Contribution

The paper presents a novel LRP-based optimization technique that minimizes background bias influence in DNNs, enhancing out-of-distribution generalization across various architectures.

Findings

ISNet outperforms eight state-of-the-art models in robustness to background bias.

The approach significantly improves generalization on external chest X-ray datasets.

It effectively reduces shortcut learning by focusing on relevant image regions.

Abstract

Features in images' backgrounds can spuriously correlate with the images' classes, representing background bias. They can influence the classifier's decisions, causing shortcut learning (Clever Hans effect). The phenomenon generates deep neural networks (DNNs) that perform well on standard evaluation datasets but generalize poorly to real-world data. Layer-wise Relevance Propagation (LRP) explains DNNs' decisions. Here, we show that the optimization of LRP heatmaps can minimize the background bias influence on deep classifiers, hindering shortcut learning. By not increasing run-time computational cost, the approach is light and fast. Furthermore, it applies to virtually any classification architecture. After injecting synthetic bias in images' backgrounds, we compared our approach (dubbed ISNet) to eight state-of-the-art DNNs, quantitatively demonstrating its superior robustness to background bias. Mixed datasets are common for COVID-19 and tuberculosis classification with chest X-rays, fostering background bias. By focusing on the lungs, the ISNet reduced shortcut learning. Thus, its generalization performance on external (out-of-distribution) test databases significantly surpassed all implemented benchmark models.