CLIP: Connecting text and images
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.
原文：https://www.a8q9.cn/en/article/clip-connecting-text-and-images-3cf9d9.html