CLIP-KD: An Empirical Study of CLIP Model Distillation

Abstract

Contrastive Language-Image Pre-training (CLIP) has become a promising language-supervised visual pre-training framework. This paper aims to distill small CLIP models supervised by a large teacher CLIP model. We propose several distillation strategies including relation feature gradient and contrastive paradigms to examine the effectiveness of CLIP-Knowledge Distillation (KD). We show that a simple feature mimicry with Mean Squared Error loss works surprisingly well. Moreover interactive contrastive learning across teacher and student encoders is also effective in performance improvement. We explain that the success of CLIP-KD can be attributed to maximizing the feature similarity between teacher and student. The unified method is applied to distill several student models trained on CC3M+12M. CLIP-KD improves student CLIP models consistently over zero-shot ImageNet classification and cross-modal retrieval benchmarks. When using ViT-L/14 pretrained on Laion-400M as the teacher CLIP-KD achieves 57.5% and 55.4% zero-shot top-1 ImageNet accuracy over ViT-B/16 and ResNet-50 surpassing the original CLIP without KD by 20.5% and 20.1% margins respectively. Our code is released on https://github.com/winycg/CLIP-KD.