PixOOD: Pixel-Level Out-of-Distribution Detection
Abstract
We propose a pixel-level out-of-distribution detection algorithm, called , which does not require training on samples of anomalous data and is not designed for a specific application which avoids 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 on a wide range of problems. It achieved state-of-the-art results on four out of seven datasets, while being competitive on the rest. The source code is available at https://github.com/vojirt/PixOOD.
Cite
Text
Vojir et al. "PixOOD: Pixel-Level Out-of-Distribution Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73027-6_6Markdown
[Vojir et al. "PixOOD: Pixel-Level Out-of-Distribution Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/vojir2024eccv-pixood/) doi:10.1007/978-3-031-73027-6_6BibTeX
@inproceedings{vojir2024eccv-pixood,
title = {{PixOOD: Pixel-Level Out-of-Distribution Detection}},
author = {Vojir, Tomas and Sochman, Jan and Matas, Jiri},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-73027-6_6},
url = {https://mlanthology.org/eccv/2024/vojir2024eccv-pixood/}
}