HyperFSAD uses sparse hypergraph matching on DINOv3 features plus dual-branch scoring to deliver training-free and language-free few-shot anomaly detection that reaches state-of-the-art on six industrial and medical datasets.
IEEE Trans
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Hypergraph-Enhanced Training-Free and Language-Free Few-Shot Anomaly Detection
HyperFSAD uses sparse hypergraph matching on DINOv3 features plus dual-branch scoring to deliver training-free and language-free few-shot anomaly detection that reaches state-of-the-art on six industrial and medical datasets.