benchmark
AnomalyShapeNet
benchmarkactiveprovisional
anomalyshapenet-4a38ee8c·1 events·first seen 16h agoAliases: AnomalyShapeNet
Co-occurring entities
More like this (12)
anomalycoweakly supervised anomaly detectionshapelet-based time-series classificationAlexNettime-series anomaly detectionAnatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning SignalHow Width and Data Shape Generalization Scaling Laws in Quadratic Neural NetworksAnysphereAWS NeuronModern Hopfield NetworkTopological Neural OperatorsSegResNet
Recent events (1)
TopoTTA integrates persistent homology into test-time adaptation for anomaly segmentation
Researchers introduce TopoTTA, a framework that incorporates persistent homology from topological data analysis into test-time adaptation (TTA) for anomaly segmentation. The method applies multi-level cubical complex filtration to anomaly score maps to generate topological pseudo-labels that guide a lightweight test-time classifier, avoiding pixel-level heuristics like confidence thresholding. Evaluated across six benchmarks including MVTec AD, VisA, and MVTec 3D-AD, TopoTTA achieves an average 15% F1 improvement over state-of-the-art unsupervised methods, with the largest gains on geometrically complex defects.