CRLD adds within-view and cross-view consistency regularisation plus confidence-based soft label mining to logit-based knowledge distillation, achieving state-of-the-art results on three benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cross-View Consistency Regularisation for Knowledge Distillation
CRLD adds within-view and cross-view consistency regularisation plus confidence-based soft label mining to logit-based knowledge distillation, achieving state-of-the-art results on three benchmarks.