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

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.

TinyDefectNet: Highly Compact Deep Neural Network Architecture for High-Throughput Manufacturing Visual Quality Inspection

“…The proposed TinyDefectNet was audited using an explainability-driven performance validation strategy to gain deeper insights into its decision-making behaviour when conducting visual quality inspection and ensure that its decisions are driven by relevant visual indicators associated with surface defects. In particular, we leverage the quantitative explainability strategy proposed in [18], which has been shown to provide good quantitative explanations that better reflect decision-making processes than other approaches in literature, and has been shown to be effective at not only model auditing [14] but also identifying hidden data issues [19]. An example of an input surface image and the corresponding quantitative explanation corresponding explanation are shown in Figure 2.…”