InCTRLv2 extends InCTRL with discriminative and one-class anomaly score learning modules to achieve state-of-the-art few-shot generalist anomaly detection and segmentation across ten datasets.
In: Proceedings of the 32nd ACM International Conference on Multimedia, pp 2041–2049
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
InCTRLv2: Generalist Residual Models for Few-Shot Anomaly Detection and Segmentation
InCTRLv2 extends InCTRL with discriminative and one-class anomaly score learning modules to achieve state-of-the-art few-shot generalist anomaly detection and segmentation across ten datasets.