About Test-time training for outlier detection
In this paper, we introduce DOUST, our method applying test-time training for outlier detection, significantly improving the detection performance. After thoroughly evaluating our algorithm on common benchmark datasets, we discuss a common problem and show that it disappears with a large enough test set. Thus, we conclude that under reasonable conditions, our algorithm can reach almost supervised performance even when no labeled outliers are given.
- Published in:
arXiv - Type:
Article - Authors:
Klüttermann, Simon; Müller, Emmanuel - Year:
2024 - Source:
https://arxiv.org/abs/2404.03495
Citation information
Klüttermann, Simon; Müller, Emmanuel: About Test-time training for outlier detection, arXiv, 2024, https://arxiv.org/abs/2404.03495, Kluettermann.Mueller.2024a,
@Article{Kluettermann.Mueller.2024a,
author={Klüttermann, Simon; Müller, Emmanuel},
title={About Test-time training for outlier detection},
journal={arXiv},
url={https://arxiv.org/abs/2404.03495},
year={2024},
abstract={In this paper, we introduce DOUST, our method applying test-time training for outlier detection, significantly improving the detection performance. After thoroughly evaluating our algorithm on common benchmark datasets, we discuss a common problem and show that it disappears with a large enough test set. Thus, we conclude that under reasonable conditions, our algorithm can reach almost supervised...}}
