Out-of-Distribution Detection using Counterfactual Distance
Quick summary
arXiv:2508.10148v2 Announce Type: replace-cross Abstract: Accurate and explainable out-of-distribution (OOD) detection is required to use machine learning systems safely. Previous work has shown that feature distance to decision boundaries can be used to identify OOD data effectively. In this paper, we build on this intuition and propose a post-hoc OOD detection method that, given an input, calculates the distance to decision boundaries by leveraging counterfactual explanations. Since computing explanations can be expensive for large architectures, we also propose strategies to improve scalabi
Key takeaways
- arXiv:2508.10148v2 Announce Type: replace-cross Abstract: Accurate and explainable out-of-distribution (OOD) detection is required to use machine learning systems safely.
- Previous work has shown that feature distance to decision boundaries can be used to identify OOD data effectively.
- In this paper, we build on this intuition and propose a post-hoc OOD detection method that, given an input, calculates the distance to decision boundaries by leveraging counterfactual explanations.
Why it matters
“Out-of-Distribution Detection using Counterfactual Distance” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.
Member comments