TACoS achieves over 96% of fully supervised segmentation performance on 2D material flakes using less than 0.6% annotated pixels via a unified framework of consistency learning, tree energy regularization, and asymmetric contrastive learning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations to Precise Segmentation
TACoS achieves over 96% of fully supervised segmentation performance on 2D material flakes using less than 0.6% annotated pixels via a unified framework of consistency learning, tree energy regularization, and asymmetric contrastive learning.