Skip to main content
PaperComputer Visionv1.0

Learning Transferable Visual Models From Natural Language Supervision (CLIP)

by OpenAI · open-source · Last verified 2026-03-17

Introduced CLIP (Contrastive Language-Image Pre-training), a model trained on 400 million image-text pairs using contrastive learning that achieves remarkable zero-shot transfer to diverse vision tasks. CLIP became foundational for vision-language alignment and generative AI pipelines.

https://arxiv.org/abs/2103.00020
A
AGreat
Adoption: A+Quality: A+Freshness: B+Citations: A+Engagement: F

Specifications

License
MIT
Pricing
open-source
Capabilities
zero-shot-classification, image-text-matching, feature-extraction, retrieval
Integrations
huggingface, openai-api
Use Cases
zero-shot-image-classification, image-retrieval, vision-language-alignment
API Available
Yes
Tags
clip, contrastive-learning, zero-shot, multimodal, vision-language
Added
2026-03-17
Completeness
100%

Index Score

82.2
Adoption
97
Quality
96
Freshness
74
Citations
97
Engagement
0

Put AI to work for your business

Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service