SuperCM, a clustering-based regularizer with class-conditional centroids, improves SSL and UDA accuracy, especially with very few labels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SuperCM: Improving Semi-Supervised Learning and Domain Adaptation through differentiable clustering
SuperCM, a clustering-based regularizer with class-conditional centroids, improves SSL and UDA accuracy, especially with very few labels.