MLDR-KD improves heterogeneous knowledge distillation by aligning decoupled class-wise and sample-wise relations at logit and feature levels, with a multiscale dynamic fusion module.
Patch slimming for efficient vision transformers, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures
MLDR-KD improves heterogeneous knowledge distillation by aligning decoupled class-wise and sample-wise relations at logit and feature levels, with a multiscale dynamic fusion module.