A multi-level transformer-CNN reconstruction model, UniAS, reports new state-of-the-art pixel-level anomaly segmentation scores on MVTec-AD and VisA, but its Dice scores rely on oracle thresholds chosen from test labels.
Masked-attention mask transformer for universal image segmentation
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Towards Accurate Unified Anomaly Segmentation
A multi-level transformer-CNN reconstruction model, UniAS, reports new state-of-the-art pixel-level anomaly segmentation scores on MVTec-AD and VisA, but its Dice scores rely on oracle thresholds chosen from test labels.