Nearest neighbor-based out-of-distribution detection via label smoothing

Dara Bahri, Heinrich Jiang, Yi Tay, Donald Metzler

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: out-of-distribution detection, nearest neighbors, label smoothing, k-NN

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Detecting out-of-distribution (OOD) examples is critical in many applications. We propose an unsupervised method to detect OOD samples using a $k$-NN density estimate with respect to a classification model's intermediate activations on in-distribution samples. We leverage a recent insight about label smoothing, which we call the {\it Label Smoothed Embedding Hypothesis}, and show that one of the implications is that the $k$-NN density estimator performs better as an OOD detection method both theoretically and empirically when the model is trained with label smoothing. Finally, we show that our proposal outperforms many OOD baselines and we also provide new finite-sample high-probability statistical results for $k$-NN density estimation's ability to detect OOD examples.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1520