OpenAI News·· 2021-01-05AI 评分38
OpenAI 发布 CLIP：连接文本与图像的神经网络
CLIP: Connecting text and images
AI 导读
OpenAI 推出名为 CLIP 的神经网络，通过自然语言监督高效学习视觉概念。该模型只需提供识别类别的名称，即可应用于任意视觉分类基准，具备类似 GPT-2 和 GPT-3 的“零样本”能力。
原文
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.
来源：OpenAI News · openai.com