DARK distillation lets a 75M-parameter student model match or exceed a 427M-parameter teacher on fetal ultrasound benchmarks by transitioning from imitating to repelling non-target similarities.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression
DARK distillation lets a 75M-parameter student model match or exceed a 427M-parameter teacher on fetal ultrasound benchmarks by transitioning from imitating to repelling non-target similarities.