Contrastive Language-Image Pretraining (CLIP)

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:model
gptkbp:architecture	gptkb:transformation vision model text model
gptkbp:author	gptkb:Ilya_Sutskever gptkb:Aditya_Ramesh gptkb:Chris_Hallacy gptkb:Gabriel_Goh gptkb:Girish_Sastry gptkb:Pamela_Mishkin gptkb:Sandhini_Agarwal gptkb:Jack_Clark gptkb:Alec_Radford gptkb:Amanda_Askell gptkb:Dario_Amodei gptkb:Jong_Wook_Kim gptkb:Miles_Brundage
gptkbp:developedBy	gptkb:OpenAI
https://www.w3.org/2000/01/rdf-schema#label	Contrastive Language-Image Pretraining (CLIP)
gptkbp:input	gptkb:illustrator gptkb:text
gptkbp:introducedIn	2021
gptkbp:language	English
gptkbp:license	gptkb:MIT_License
gptkbp:memiliki_tugas	image classification zero-shot learning image-text retrieval
gptkbp:notableFor	transfer learning multimodal learning zero-shot image classification
gptkbp:notablePublication	gptkb:Learning_Transferable_Visual_Models_From_Natural_Language_Supervision
gptkbp:openSource	yes
gptkbp:output	joint embedding
gptkbp:trainer	contrastive learning 400 million image-text pairs
gptkbp:usedIn	gptkb:DALL-E gptkb:Stable_Diffusion
gptkbp:bfsParent	gptkb:Google_Brain_(former)
gptkbp:bfsLayer	7