Two4Two: Evaluating Interpretable Machine Learning - A Synthetic Dataset For Controlled Experiments
arXiv:2105.02825
Abstract
A growing number of approaches exist to generate explanations for image classification. However, few of these approaches are subjected to human-subject evaluations, partly because it is challenging to design controlled experiments with natural image datasets, as they leave essential factors out of the researcher's control. With our approach, researchers can describe their desired dataset with only a few parameters. Based on these, our library generates synthetic image data of two 3D abstract animals. The resulting data is suitable for algorithmic as well as human-subject evaluations. Our user study results demonstrate that our method can create biases predictive enough for a classifier and subtle enough to be noticeable only to every second participant inspecting the data visually. Our approach significantly lowers the barrier for conducting human subject evaluations, thereby facilitating more rigorous investigations into interpretable machine learning. For our library and datasets see, https://github.com/mschuessler/two4two/
arXiv comment6 pages, 3 figures, presented at the ICLR 2021 RAI workshop
References in corpus (5)
- Towards A Rigorous Science of Interpretable Machine Learning
- Sanity Checks for Saliency Maps
- A systematic review and taxonomy of explanations in decision support and recommender systems
- Towards falsifiable interpretability research
- Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction