Dual Student trains two independent student networks with a stabilization constraint that transfers only confident, perturbation-invariant predictions, improving semi-supervised classification over EMA-teacher baselines.
Combining labeled and un- labeled data with co-training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning
Dual Student trains two independent student networks with a stabilization constraint that transfers only confident, perturbation-invariant predictions, improving semi-supervised classification over EMA-teacher baselines.