Poster
PixOOD: Pixel-Level Out-of-Distribution Detection
Tomas Vojir · Jan Sochman · Jiri Matas
# 21
[
Abstract
]
[ Project Page ]
[ Paper PDF ]
[
Poster]
[
Supplemental]
Tue 1 Oct 7:30 a.m. PDT
— 9:30 a.m. PDT
Abstract:
We propose a dense image prediction out-of-distribution detection algorithm, called PixOOD, which does not require training on samples of anomalous data and is not designed for a specific application which helps avoiding traditional training biases. In order to model the complex intra-class variability of the in-distribution data at the pixel level, we propose an online data condensation algorithm which is more robust than standard K-means and is easily trainable through SGD. We evaluate PixOOD on a wide range of problems and achieve state-of-the-art results on four out of seven datasets. The source code will be released upon acceptance.
Chat is not available.