CLIP: Connecting text and images
核心要点速览
We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the “zero-shot” capabilities of GPT-2 and GPT-3.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。