DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression

Abstract

Compressing vision-language models for on-device deployment is increasingly important in clinical settings, but knowledge distillation (KD) degrades sharply when the teacher-student capacity gap spans an order of magnitude or more. We argue that, under such gaps, strict imitation of the teacher is a poor objective: much of the teacher's pairwise similarity structure reflects its own architectural biases rather than information a compact student can efficiently represent. We propose \textbf{Diagonal-Anchored Repulsive Knowledge Distillation (DARK)}, a contrastive KD framework that decomposes the distillation loss into a diagonal term (matched image-text pairs) and an off-diagonal term (non-target similarities). The diagonal term anchors matched-pair alignment throughout training; the off-diagonal term is annealed from positive to negative weighting, transitioning the student from imitating to \emph{repelling} the teacher's non-target similarity structure. We instantiate DARK by distilling FetalCLIP, a 427M-parameter fetal ultrasound vision-language model, into \textbf{MobileFetalCLIP}, a 75M-parameter student model with a $26\times$ smaller visual encoder, running in 1.6\,ms on an iPhone~16~Pro. The student matches or exceeds its teacher on three zero-shot benchmarks, including HC18 biometry validity (88.6\% vs.\ 83.5\%) and brain sub-plane F1 (0.784 vs.\ 0.702). Embedding-geometry and logit analyses show that DARK induces \emph{structured decorrelation}: the student preserves teacher-aligned per-image confidence while diverging from inherited inter-class confusion, suggesting that controlled repulsion can be more efficient than imitation under extreme compression.