[Imnimo]

Well, the text encoder sees the ascii characters s-p-i-d-e-r (after byte-pair encoding). That's different from seeing a photograph of a piece of paper that says "spider" on it. It's not surprising that the network can associate a picture of spiderman with a caption that contains the text "spider", but rather that the same neuron lights up when you show it a piece of paper that says "spider" as when you show it a picture of spiderman.

[chromanoid]

Maybe I don't get something about CLIP. But won't there the same labels and as a result the same pairings for a written piece of paper with spider on it and a picture of Spiderman?

[Imnimo]

The labels are just whatever people on the internet wrote next to the image. Certainly there are some instances of things like "this is a picture that says 'spider'" or whatever (probably a little more natural than that), or else the network would have no way of learning to read. But what's interesting here is that it's the same neuron doing the reading and doing the recognizing of Spiderman's head. That's not the only way that it could have solved the problem. There could have been some dimensions of the representation vector used for reading text, and other for recognizing visual objects, and those would be handled by separate subsets of neurons in the network.

[chromanoid]

Maybe it just recognizes pixel soups? Why should it know the difference between a piece of text and a real spider? It's just our interpretation of the image that makes it "multi-modal". CLIP probably just categorizes certain kinds of white and black patterns as a special kind of spider that happens to also look like a piece of paper and instances of text.

[Imnimo]

I mean, yeah, it does just recognize pixel soups - all the neurons are just semi-scrutable combinations of other features. It's probably the case that there are some early neurons that recognize various letters, and so you'd have some subset of neurons that are shared between the "spiderman" neuron circuit and the circuits that are used by other neurons that recognize other words. I don't know how much credit you'd give that for "reading", but I'd say it at least would qualify as multi-modal.

[chromanoid]

So if the network can recognize species by their rear view you would consider it also multi-modal? Because that is what I am trying to tell... there are probably no higher level concepts here, just various different pixel soups that happen to need the same label.

[mrow84]

If the trained network produces common labels for sets of pixel soups that we consider to be semantically related, but are not visually related, then that is interesting.