Towards Explaining Image-Based Distribution Shifts

Sean Kulinski, David I. Inouye; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 4788-4792


Distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing the accuracy of downstream models. Thus, understanding such distribution shifts is critical for examining and hopefully mitigating the effect of such a shift. Most prior work has focused on either natively handling distribution shift (e.g., Domain Generalization) or merely detecting a shift while assuming any detected shift can be understood and handled appropriately by a human operator. For the latter, we hope to aid in these manual mitigation tasks by explaining the distribution shift to an operator. To this end, we suggest two methods: providing a set of interpretable mappings from the original distribution to the shifted one or providing a set of distributional counterfactual examples. We provide preliminary experiments on these two methods, and discuss important concepts and challenges for moving towards a better understanding of image-based distribution shifts.

Related Material

[pdf] [supp]
@InProceedings{Kulinski_2022_CVPR, author = {Kulinski, Sean and Inouye, David I.}, title = {Towards Explaining Image-Based Distribution Shifts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4788-4792} }