SuperCM uses class-wise moving-average centroids to add a Gaussian-mixture clustering loss to a supervised classifier, improving CIFAR-10 SSL accuracy at low label counts.
We follow the recommendations of [17] for data pre- possessing, model architecture, and training protocol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Supercm: Revisiting Clustering for Semi-Supervised Learning
SuperCM uses class-wise moving-average centroids to add a Gaussian-mixture clustering loss to a supervised classifier, improving CIFAR-10 SSL accuracy at low label counts.