Skip to content
AI Atlas
PaperActive

CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation

arxiv.org/abs/2603.25383

Updated 50 min ago · first seen 11 Sept 2026

paper_01M294H3522JF7CP6T0X2VJ9MF

Published
11 Sept 2026
T1 · 50 min ago
arXiv
2603.25383
T1 · 50 min ago
Category
cs.CV
T1 · 50 min ago

Abstract

Contrastive Language-Image Pre-training (CLIP) demonstrates strong zero-shot generalization, but due to substantial computational and memory costs, distillation into lightweight models is required. Existing relational objectives do not explicitly model multidirectional relationships between teacher and student embeddings, potentially leaving the geometric relationships insufficiently constrained. This may disrupt the modality-gap structure important for zero-shot transfer. To address these limitations, we propose a relational distillation framework, CLIP-RD, which introduces two relational methods, Vertical Relational Distillation (VRD) and Cross Relational Distillation (XRD). VRD aligns teacher-student intra-modal similarity distributions to enforce consistent distillation strength across image and text embeddings. Meanwhile, XRD aligns the teacher-image-student-text and teacher-text-student-image similarity distributions to impose bidirectional cross-modal symmetry. By jointly modeling these multidirectional relational structures, CLIP-RD aligns the student's embedding geometry more faithfully to the teacher's, outperforming CLIP-KD by 1.8%p. This performance improvement is maintained across diverse architectures, teacher scales, retrieval tasks, downstream tasks, and corruption settings, with negligible additional training-time overhead.

Authors 5

Jeannie Chung, Hanna Jang, Ingyeong Yang, Uiwon Hwang, Jaehyeong Sim

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

arXiv id
2603.25383

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Categories
cs.CV

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Primary category
cs.CV

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

50 min ago

Conflicts

None