OpenAI Blog company blog
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.
- Points
- 119
- HN comments
- 10
- Submissions
- 1
- Cited by
- 29 commenters
AI & Machine LearningSoftware Engineering2021
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jan 5, 2021 | Clip: Connecting Text and Images by sama | 119 | 10 |
Cited in comments
Linked from 33 Hacker News comments by 29 different people, from Jan 2021 to Nov 2022.
Most recent:
