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

arXiv: https://arxiv.org/abs/2106.09177 · HTML: https://mlsanity.com/paper/2106.09177/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 10 of 10)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images](https://mlsanity.com/paper/2003.09871/) (2020)
- [Large image datasets: A pyrrhic win for computer vision?](https://mlsanity.com/paper/2006.16923/) (2020)
- [MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis](https://mlsanity.com/paper/2010.14925/) (2020)
- [COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest CT Images](https://mlsanity.com/paper/2009.05383/) (2020)
- [Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms](https://mlsanity.com/paper/1910.07387/) (2019)
- [COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 from Chest CT Images Through Bigger, More Diverse Learning](https://mlsanity.com/paper/2101.07433/) (2021)
- [Auditing ImageNet: Towards a Model-driven Framework for Annotating Demographic Attributes of Large-Scale Image Datasets](https://mlsanity.com/paper/1905.01347/) (2019)
- [COVID-Net S: Towards computer-aided severity assessment via training and validation of deep neural networks for geographic extent and opacity extent scoring of chest X-rays for SARS-CoV-2 lung disease severity](https://mlsanity.com/paper/2005.12855/) (2020)
- [Fibrosis-Net: A Tailored Deep Convolutional Neural Network Design for Prediction of Pulmonary Fibrosis Progression from Chest CT Images](https://mlsanity.com/paper/2103.04008/) (2021)

## Built on by (most cited first, 1 of 1)

- [TinyDefectNet: Highly Compact Deep Neural Network Architecture for High-Throughput Manufacturing Visual Quality Inspection](https://mlsanity.com/paper/2111.14319/) (2021)

## Abstract (arXiv)

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.