Long-Tailed Anomaly Detection with Learnable Class Names

arXiv:2403.20236v1 Announce Type: new
Abstract: Anomaly detection (AD) aims to identify defective images and localize their defects (if any). Ideally, AD models should be able to detect defects over many image classes; without relying on hard-coded class names that can be uninformative or inconsistent across datasets; learn without anomaly supervision; and be robust to the long-tailed distributions of real-world applications. To address these challenges, we formulate the problem of long-tailed AD by introducing several datasets with different levels of class …

anomaly anomaly detection arxiv class cs.cv detection type