Class-split anomaly detection benchmarks can yield collapsing or inverted anomaly scores when the held-out class overlaps normal data in representation space, with neighborhood class leakage predicting this instability across image datasets.
ACM Computing Surveys , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
Class-split anomaly detection benchmarks can yield collapsing or inverted anomaly scores when the held-out class overlaps normal data in representation space, with neighborhood class leakage predicting this instability across image datasets.