What is Wrong with One-Class Anomaly Detection?

20 Apr 2021  ·  JuneKyu Park, Jeong-Hyeon Moon, Namhyuk Ahn, Kyung-Ah Sohn ·

From a safety perspective, a machine learning method embedded in real-world applications is required to distinguish irregular situations. For this reason, there has been a growing interest in the anomaly detection (AD) task. Since we cannot observe abnormal samples for most of the cases, recent AD methods attempt to formulate it as a task of classifying whether the sample is normal or not. However, they potentially fail when the given normal samples are inherited from diverse semantic labels. To tackle this problem, we introduce a latent class-condition-based AD scenario. In addition, we propose a confidence-based self-labeling AD framework tailored to our proposed scenario. Since our method leverages the hidden class information, it successfully avoids generating the undesirable loose decision region that one-class methods suffer. Our proposed framework outperforms the recent one-class AD methods in the latent multi-class scenarios.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here