Interpretable Distribution Shift Detection using Optimal Transport
Not on the map. Why?
Abstract (arXiv)
We propose a method to identify and characterize distribution shifts in classification datasets based on optimal transport. It allows the user to identify the extent to which each class is affected by the shift, and retrieves corresponding pairs of samples to provide insights on its nature. We illustrate its use on synthetic and natural shift examples. While the results we present are preliminary, we hope that this inspires future work on interpretable methods for analyzing distribution shifts.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 8 of its 12 references that are in the map. First posted on arXiv 4 Aug 2022.
Builds on
8 of 12 references.
References · 8
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,327
- 2020Energy-based Out-of-distribution Detectioncited by 1,297
- 2018Computational Optimal Transportcited by 772
- 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 296
- 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
- 2020Geometric Dataset Distances via Optimal Transportcited by 158
- 2020Robust Out-of-distribution Detection for Neural Networkscited by 57
- 2021Zero-Shot Day-Night Domain Adaptation with a Physics Priorcited by 47
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.