# Learning Interpretable Features via Adversarially Robust Optimization

arXiv: https://arxiv.org/abs/1905.03767 · HTML: https://mlsanity.com/paper/1905.03767/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2019.

## Built on by (most cited first, 8 of 8)

- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [Neural Response Interpretation through the Lens of Critical Pathways](https://mlsanity.com/paper/2103.16886/) (2021)
- [Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models](https://mlsanity.com/paper/2209.12420/) (2022)
- [Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features](https://mlsanity.com/paper/2104.00411/) (2021)
- [Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models](https://mlsanity.com/paper/2104.02481/) (2021)
- [Automatic Infectious Disease Classification Analysis with Concept Discovery](https://mlsanity.com/paper/2209.02415/) (2022)
- [Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models](https://mlsanity.com/paper/2204.01729/) (2022)

## Abstract (arXiv)

Neural networks are proven to be remarkably successful for classification and diagnosis in medical applications. However, the ambiguity in the decision-making process and the interpretability of the learned features is a matter of concern. In this work, we propose a method for improving the feature interpretability of neural network classifiers. Initially, we propose a baseline convolutional neural network with state of the art performance in terms of accuracy and weakly supervised localization. Subsequently, the loss is modified to integrate robustness to adversarial examples into the training process. In this work, feature interpretability is quantified via evaluating the weakly supervised localization using the ground truth bounding boxes. Interpretability is also visually assessed using class activation maps and saliency maps. The method is applied to NIH ChestX-ray14, the largest publicly available chest x-rays dataset. We demonstrate that the adversarially robust optimization paradigm improves feature interpretability both quantitatively and visually.