Insights into Data through Model Behaviour: An Explainability-driven Strategy for Data Auditing for Responsible Computer Vision Applications

TL;DR

This paper introduces an explainability-driven data auditing strategy that uncovers hidden data quality issues in medical datasets, improving model behavior and promoting responsible AI development in computer vision.

Contribution

It presents a novel explainability-based approach to data auditing that identifies data issues affecting model predictions, enhancing model reliability and interpretability.

Findings

Discovered hidden data quality issues in medical datasets.

Improved model prediction behavior through data issue remediation.

Validated strategy on popular medical benchmark datasets.

Abstract

In this study, we take a departure and explore an explainability-driven strategy to data auditing, where actionable insights into the data at hand are discovered through the eyes of quantitative explainability on the behaviour of a dummy model prototype when exposed to data. We demonstrate this strategy by auditing two popular medical benchmark datasets, and discover hidden data quality issues that lead deep learning models to make predictions for the wrong reasons. The actionable insights gained from this explainability driven data auditing strategy is then leveraged to address the discovered issues to enable the creation of high-performing deep learning models with appropriate prediction behaviour. The hope is that such an explainability-driven strategy can be complimentary to data-driven strategies to facilitate for more responsible development of machine learning algorithms for computer vision applications.