CLIP: Learning Transferable Visual Models From Natural Language Supervision
📌 核心贡献
该论文提出一种利用海量图像-文本对进行自然语言监督学习的新方法，解决了传统视觉模型依赖固定类别、泛化性差的问题。其核心创新在于通过预测图片与描述的匹配关系进行预训练，从而高效学习SOTA视觉表示，并实现对新视觉概念的零样本迁移。
📖 摘要
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 发表 | 2021-02-26 |
| 分类 | cs.CV, cs.LG |
| 链接 | arXiv |