Artificial Intelligence

    

Self-supervised Out-of-distribution Detection with Dynamic Latent Scale GAN

Authors: Jeongik Cho

Dynamic latent scale GAN proposed a learning-based GAN inversion method with maximum likelihood estimation. In this paper, we propose a method for self-supervised out-of-distribution detection using the encoder of dynamic latent scale GAN. When the dynamic latent scale GAN converged, since the entropy of the scaled latent random variable is optimal to represent in-distribution data, in-distribution data is densely mapped to latent codes with high likelihood. This enables the log-likelihood of the predicted latent code to be used for out-of-distribution detection. The proposed method does not require mutual information of in-distribution data and additional hyperparameters for prediction. The proposed method also showed better out-of-distribution detection performance than the previous state-of-art method.

Comments: 8 Pages.

Download: PDF

Submission history

[v1] 2022-02-18 16:47:41
[v2] 2022-02-22 15:03:45
[v3] 2022-04-12 05:22:42

Unique-IP document downloads: 478 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus