Improving Normalizing Flows with the Approximate Mass for Out-of-Distribution Detection

Samy Chali, Inna Kucher, Marc Duranton, Jacques-Olivier Klein

CVPRW 2023 pp. 750-758

doi:10.1109/CVPRW59228.2023.00082 /cvprw/2023/chali2023cvprw-improving/

Abstract

Normalizing flows are generative models that show poor performance on out-of-distribution (OOD) detection tasks with a likelihood-based test. In this study we focus on the "approximate mass" metric. We show that while it improves OOD detection performance, it has limitations under a maximum likelihood training. To solve this limitation we modify the training objective by incorporating the approximate mass. It smooths the learnt distribution in the vicinity of training in-distribution data. We measure an average of 97.6% AUROC in our experiments on different benchmarks, showing an improvement of 16% with respect to the best baseline we tested against.

PDF CVPRW Semantic Scholar

Cite

Text

Chali et al. "Improving Normalizing Flows with the Approximate Mass for Out-of-Distribution Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00082

Markdown

[Chali et al. "Improving Normalizing Flows with the Approximate Mass for Out-of-Distribution Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/chali2023cvprw-improving/) doi:10.1109/CVPRW59228.2023.00082

BibTeX

@inproceedings{chali2023cvprw-improving,
  title     = {{Improving Normalizing Flows with the Approximate Mass for Out-of-Distribution Detection}},
  author    = {Chali, Samy and Kucher, Inna and Duranton, Marc and Klein, Jacques-Olivier},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {750-758},
  doi       = {10.1109/CVPRW59228.2023.00082},
  url       = {https://mlanthology.org/cvprw/2023/chali2023cvprw-improving/}
}