TY  - JOUR
TI  - Learning Transferable Visual Models From Natural Language Supervision (CLIP)
AU  - Radford, A.
AU  - Kim, J. W.
AU  - Hallacy, C.
AU  - Ramesh, A.
AU  - Goh, G.
AU  - Agarwal, S.
AU  - Sastry, G.
AU  - Askell, A.
AU  - Mishkin, P.
AU  - Clark, J.
AU  - Krueger, G.
AU  - Sutskever, I.
PY  - 2021
DA  - 2021/02//
JO  - ICML 2021
AB  - Radford et al. (2021) trained a model to align image and text representations in a shared embedding space using contrastive learning on 400 million web-scraped image-caption pairs. The resulting CLIP model can match images to natural-language descriptions with strong zero-shot performance. CLIP is the component that allows text prompts to steer image-generation models: Stable Diffusion, DALL-E and CLIP-guided diffusion all depend on its joint embedding to translate a prompt into the visual direction for the generative process. Explaining prompt-to-image generation to animation students requires understanding CLIP's role as the semantic bridge between language and image space.
KW  - generative-ai
KW  - image-generation
KW  - ai-literacy
UR  - https://arxiv.org/abs/2103.00020
LA  - en
ER  -