Contrastive Language–Image Pre-training

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:model
gptkbp:abbreviation	gptkb:CLIP
gptkbp:architecture	gptkb:transformation text transformer vision transformer
gptkbp:arXivID	2103.00020
gptkbp:author	gptkb:Ilya_Sutskever gptkb:Aditya_Ramesh gptkb:Chris_Hallacy gptkb:Gabriel_Goh gptkb:Girish_Sastry gptkb:Mark_Chen gptkb:Pamela_Mishkin gptkb:Sandhini_Agarwal gptkb:Jack_Clark gptkb:Alec_Radford gptkb:Amanda_Askell gptkb:Jong_Wook_Kim gptkb:Miles_Brundage
gptkbp:developedBy	gptkb:OpenAI
https://www.w3.org/2000/01/rdf-schema#label	Contrastive Language–Image Pre-training
gptkbp:influenced	gptkb:Florence gptkb:ALIGN gptkb:BLIP gptkb:DALL-E gptkb:Stable_Diffusion
gptkbp:input	gptkb:illustrator gptkb:text
gptkbp:introducedIn	2021
gptkbp:license	gptkb:MIT_License_(for_OpenCLIP)
gptkbp:memiliki_tugas	image classification zero-shot learning
gptkbp:notableFor	gptkb:OpenAI_CLIP gptkb:Hugging_Face_Transformers gptkb:OpenCLIP
gptkbp:notablePublication	gptkb:Learning_Transferable_Visual_Models_From_Natural_Language_Supervision
gptkbp:openSource	yes
gptkbp:output	image-text similarity score
gptkbp:publishedIn	gptkb:arXiv
gptkbp:trainer	gptkb:LAION-400M gptkb:Conceptual_Captions gptkb:YFCC100M contrastive learning image-text pairs
gptkbp:usedFor	content moderation image search image captioning visual question answering
gptkbp:bfsParent	gptkb:CLIP
gptkbp:bfsLayer	6