Dual-head knowledge distillation partitions the linear classifier into separate heads for logit and probability losses to exploit logits without causing classification head collapse.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
Dual-head knowledge distillation partitions the linear classifier into separate heads for logit and probability losses to exploit logits without causing classification head collapse.