Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
This work addresses the problem of diagnosing model reliability for researchers and practitioners, though it is incremental as it builds on existing methods like Textual Inversion.
The paper tackles the challenge of evaluating machine learning models under distribution shift by introducing dataset interfaces, which generate counterfactual examples with specified shifts, and demonstrates their application on ImageNet to study model failures across variations like background and lighting.
Distribution shift is a major source of failure for machine learning models. However, evaluating model reliability under distribution shift can be challenging, especially since it may be difficult to acquire counterfactual examples that exhibit a specified shift. In this work, we introduce the notion of a dataset interface: a framework that, given an input dataset and a user-specified shift, returns instances from that input distribution that exhibit the desired shift. We study a number of natural implementations for such an interface, and find that they often introduce confounding shifts that complicate model evaluation. Motivated by this, we propose a dataset interface implementation that leverages Textual Inversion to tailor generation to the input distribution. We then demonstrate how applying this dataset interface to the ImageNet dataset enables studying model behavior across a diverse array of distribution shifts, including variations in background, lighting, and attributes of the objects. Code available at https://github.com/MadryLab/dataset-interfaces.