Encyclopedia · 311 concepts
Learn this concept as a feed

Computer Vision · advanced · concept 162 of 311 · Updated Nov 4, 2026

Contrastive Learning & CLIP

Train two encoders so matching pairs land close in embedding space and mismatched pairs land far apart. CLIP did this for 400 million image-caption pairs and got zero-shot classification for free: name the classes in English and it picks one. The bridge most multimodal systems stand on.

L7 · LLM and generative AI engineerDevelopersTech leadersQA and testing

Top AI contributors on this

Key terms

Contrastive lossShared embedding spaceZero-shot classificationImage-text pairsInfoNCE

Learn these first

Where you meet it in the real world

Visual search, image moderation, the text encoder guiding Stable Diffusion, dataset curation

Videos

Guides and articles

This unlocks