English

CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination

Computer Vision and Pattern Recognition 2024-12-17 v2

Abstract

Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption of computational resources. Although knowledge distillation has been widely applied in single modality models, how to efficiently expand knowledge distillation to vision-language foundation models with extensive data remains relatively unexplored. In this paper, we introduce CLIP-CID, a novel distillation mechanism that effectively transfers knowledge from a large vision-language foundation model to a smaller model. We initially propose a simple but efficient image semantic balance method to reduce transfer learning bias and improve distillation efficiency. This method filters out 43.7% of image-text pairs from the LAION400M while maintaining superior performance. After that, we leverage cluster-instance discrimination to facilitate knowledge transfer from the teacher model to the student model, thereby empowering the student model to acquire a holistic semantic comprehension of the pre-training data. Experimental results demonstrate that CLIP-CID achieves state-of-the-art performance on various downstream tasks including linear probe and zero-shot classification.

Keywords

Cite

@article{arxiv.2408.09441,
  title  = {CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination},
  author = {Kaicheng Yang and Tiancheng Gu and Xiang An and Haiqiang Jiang and Xiangzi Dai and Ziyong Feng and Weidong Cai and Jiankang Deng},
  journal= {arXiv preprint arXiv:2408.09441},
  year   = {2024}
}

Comments

Accepted by AAAI 2025

R2 v1 2026-06-28T18:15:53.517Z