Downgrading the top MLP blocks of a fine-tuned ViT and using large-radius SAM during fine-tuning improves knowledge distillation to small students by preserving mutual information between inputs and teacher outputs.
org/CorpusID:231573431
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
-
ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation
Downgrading the top MLP blocks of a fine-tuned ViT and using large-radius SAM during fine-tuning improves knowledge distillation to small students by preserving mutual information between inputs and teacher outputs.