A saturation gate measures the reliability of a teacher's confident pseudo-labels, Pr(correct | confidence >= 0.95), and picks strict filtering when that reliability is high and an adaptive floor when it drops, making the correct call on six DINOv2 teachers.
Softmatch: Addressing the quantity-quality tradeoff in semi-supervised learning,
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
-
CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers
A saturation gate measures the reliability of a teacher's confident pseudo-labels, Pr(correct | confidence >= 0.95), and picks strict filtering when that reliability is high and an adaptive floor when it drops, making the correct call on six DINOv2 teachers.