A training-only semantic branch corrects hard-token assignments and aligns class centers, improving semi-supervised medical image segmentation without inference overhead.
TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers,
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
-
SHTA: Semantic Hard Token Correction and Center Alignment for Semi-Supervised Medical Image Segmentation
A training-only semantic branch corrects hard-token assignments and aligns class centers, improving semi-supervised medical image segmentation without inference overhead.