Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark 事件

Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark arXiv:2605.26068v1 Announce Type: cross Abstract: Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision. However, these directions remain isolated, lacking a unified framework to assess whether they address unique challenges or share fundamental mechanics. This paper introduces WSADBench, the first benchmark that unifies evaluation across di