PixOOD: Pixel-Level Out-of-Distribution Detection

Summary

PixOOD is a pixel-level out-of-distribution detection algorithm that needs no training on anomalous samples and is not tied to one application. It models in-distribution data with an online data condensation algorithm, which the authors describe as more robust than standard K-means and trainable by stochastic gradient descent, paired with per-class or unified calibration models for the decision strategy. It achieved state-of-the-art results on four of seven datasets and was competitive on the rest.