CS PAPERS DEEP-READ · PAPER 6

CLIP: Teaching Machines to See with Natural Language

Radford et al. · OpenAI · ICML 2021

中文 →

What did this paper do?

In 2021, OpenAI (the company that later built ChatGPT) released CLIP. Instead of hiring people to label images, it collected 400 million pairs of "image + the text written next to it" from the internet, and had a machine learn one skill: telling whether a picture and a sentence are about the same thing. Once trained, it can recognize thousands of things it was never specifically taught — with no retraining. When you generate images from text today (Stable Diffusion, DALL·E) or search photos with a sentence, CLIP is working behind the scenes.

The old world's problem

Before this, teaching machines to see was like running a school that only gives multiple-choice exams. You hired an army of people to hand-label millions of images — "cat," "dog," "airplane" — and the machine memorized them. Expensive and slow, but the worst part: learn a thousand categories, and that's all it will ever know. Want it to also recognize "skateboard"? Collect new images, label them, retrain. And it only knew numbers, not meanings — "cat" was just option #281 to it, with no connection to what cats are or do.

The idea

CLIP's idea: the teacher has been sitting on the internet for free all along. Nearly every image online comes with words written by a human — captions, titles, descriptions. So drop the multiple-choice exams and play a matching game instead: hand the machine a stack of photos and a shuffled stack of captions, and have it figure out which picture goes with which sentence. Wrong matches, adjust; repeat. Nobody has to write exam questions, and the supply of questions is nearly infinite.

How does it recognize things it was never taught?

To win the matching game, the machine had to train two translators: one turns any picture into a kind of internal "meaning coordinate," the other turns any sentence into the same coordinate system — so a picture and a sentence about the same thing land right next to each other, like two neighboring shops on a map.

To recognize something new, you just name the candidates in words: give the text translator "a photo of a skateboard," "a photo of a cat," and give the image translator the photo in question — then see which sentence the picture lands closest to. Because it already met the meaning of "skateboard" during the matching game, no new training is needed: writing a sentence conjures a brand-new recognizer on the spot. Categories are no longer a fixed answer sheet — they're whatever you can say.

What it unlocked

Vision got plumbed into language. To generate "a corgi riding a skateboard," a machine first needs to know what images that sentence is close to in meaning — the shared coordinate system CLIP learned is exactly the foundation that text-to-image models like Stable Diffusion and DALL·E were built on, and most of today's multimodal assistants (AIs that chat about images) use CLIP's "image translator" as their eyes. One honest caveat: it's great at "what is this," but counting objects or telling near-identical car models apart still trips it up.

Remember one thing

Instead of paying people to label images, let the machine play a matching game on 400 million free "image + caption" pairs from the web, learning to put pictures and words into one shared "meaning space" — so recognizing something new takes no retraining: one written sentence is one new recognizer. That shared space became the foundation of text-to-image and multimodal AI.

Want the matching-game diagram, real numbers, and where it fails? → switch to the deep read