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

arXiv: https://arxiv.org/abs/2408.09441 · HTML: https://mlsanity.com/paper/2408.09441/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 43 of its 65 references that are in the map.
- First posted on arXiv 18 Aug 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)
- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [SemDeDup: Data-efficient learning at web-scale through semantic deduplication](https://mlsanity.com/paper/2303.09540/) (2023)
- [Online Deep Clustering for Unsupervised Representation Learning](https://mlsanity.com/paper/2006.10645/) (2020)
- [Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation](https://mlsanity.com/paper/2205.14141/) (2022)
- [Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training](https://mlsanity.com/paper/2301.02280/) (2023)
- [TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance](https://mlsanity.com/paper/2309.12314/) (2023)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)

## Built on by (most cited first, 21 of 21)

- [Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs](https://mlsanity.com/paper/2504.17432/) (2025)
- [UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning](https://mlsanity.com/paper/2510.13515/) (2025)
- [Active Data Curation Effectively Distills Large-Scale Multimodal Models](https://mlsanity.com/paper/2411.18674/) (2024)
- [Region-based Cluster Discrimination for Visual Representation Learning](https://mlsanity.com/paper/2507.20025/) (2025)
- [Decoupled Global-Local Alignment for Improving Compositional Understanding](https://mlsanity.com/paper/2504.16801/) (2025)
- [RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm](https://mlsanity.com/paper/2502.12513/) (2025)
- [Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval](https://mlsanity.com/paper/2509.09118/) (2025)
- [Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval](https://mlsanity.com/paper/2510.22765/) (2025)
- [Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning](https://mlsanity.com/paper/2603.13341/) (2026)
- [Multimodal Medical Image Binding via Shared Text Embeddings](https://mlsanity.com/paper/2506.18072/) (2025)
- [Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization](https://mlsanity.com/paper/2505.07675/) (2025)
- [FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation](https://mlsanity.com/paper/2505.18053/) (2025)
- [ForCenNet: Foreground-Centric Network for Document Image Rectification](https://mlsanity.com/paper/2507.19804/) (2025)
- [Spotlighter: Revisiting Prompt Tuning from a Representative Mining View](https://mlsanity.com/paper/2509.00905/) (2025)
- [ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder](https://mlsanity.com/paper/2510.18795/) (2025)
- [A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization](https://mlsanity.com/paper/2510.20291/) (2025)
- [CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance](https://mlsanity.com/paper/2412.03871/) (2024)
- [Multi-Sequence Parotid Gland Lesion Segmentation via Expert Text-Guided Segment Anything Model](https://mlsanity.com/paper/2508.09645/) (2025)
- [DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset](https://mlsanity.com/paper/2601.10305/) (2026)
- [TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings](https://mlsanity.com/paper/2603.00136/) (2026)
- [Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Models](https://mlsanity.com/paper/2609.16689/) (2026)

## Abstract (arXiv)

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.