BicKD introduces a bilateral contrastive loss in knowledge distillation that strengthens class-wise orthogonality and intra-class consistency in predictive distributions, outperforming prior logit-based methods.
Continual learning with knowl- edge distillation: A survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BicKD: Bilateral Contrastive Knowledge Distillation
BicKD introduces a bilateral contrastive loss in knowledge distillation that strengthens class-wise orthogonality and intra-class consistency in predictive distributions, outperforming prior logit-based methods.