Decomposing texture and semantic for out-of-distribution detection

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

Abstract: Highlights•We decompose the “unclear” definition of the ID into texture and semantics.•Motivated by real-world problems, we create a new OOD detection benchmark.•No auxiliary information is needed in our method, unlike previous models.•Our novel method is effective for both texture and semantic properties.