Decomposing Texture and Semantics for Out-of-distribution Detection

Jeong-Hyeon Moon, Namhyuk Ahn, Kyung-Ah Sohn

Keywords: Out-of-distribution detection, Fourier analysis, Normailzing flow model

TL;DR: We propose a novel OOD detection framework that decomposes the definition of the in-distribution as texture and semantics.

Abstract: Out-of-distribution (OOD) detection has made significant progress in recent years because the distribution mismatch between the training and testing can severely deteriorate the reliability of a machine learning system.Nevertheless, the lack of precise interpretation of the in-distribution limits the application of OOD detection methods to real-world system pipielines. To tackle this issue, we decompose the definition of the in-distribution into texture and semantics, motivated by real-world scenarios. In addition, we design new benchmarks to measure the robustness that OOD detection methods should have. To achieve a good balance between the OOD detection performance and robustness, our method takes a divide-and-conquer approach. That is, the model first tackles each component of the texture and semantics separately, and then combines them later. Such design philosophy is empirically proven by a series of benchmarks including not only ours but also the conventional counterpart.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)