Would you say they have Blindsight?
Vision language models are blind
51–60 of 202 posts
Re: Vision language models are blind
#52I don't like this paper for the following reasons:
- The language is unnecessarily scathing
- They repeatedly show data where the models are getting things right 70, 80, 90% of the time, and then show a list of what they call "qualitative samples" (what does "qualitative" mean? "cherry-picked"?) which look very bad. But it got the answer right 70/80/90% of the time! That's hardly "blind"...
- Various of the tasks hinge on the distinction between two objects "exactly touching" vs. "very nearly touching" vs. "very slightly overlapping", a problem which (i) is hard for humans and (ii) is particularly (presumably deliberately) sensitive to resolution/precision, where we should not be surprised that models fail
- The main fish-shaped example given in task 1 seems genuinely ambiguous to me - do the lines "intersect" once or twice? The tail of the fish clearly has a crossing, but the nose of the fish seems a bit fishy to me... is that really an intersection?
- AFAIC deranged skepticism is just as bad as deranged hype, the framing here is at risk of appealing to the former
It's absolutely fair to make the point that these models are not perfect, fail a bunch of the time, and to point out the edge cases where they suck. That moves the field forwards. But the hyperbole (as pointed out by another commenter) is very annoying.
Re: Vision language models are blind
#53Current approaches of multi-modal models work on embeddings and tokenizations of images, which is the fundamental problem: you are feeding blurry, non-precise data into the model. Yes, they are blind because of exactly this. An embedding isn't conceptually that much different from feeding a 1024-word description of an image instead of the actual image. At the moment compute power isn't good enough to feed high-res pi…
> An embedding isn't conceptually that much different from feeding a 1024-word description of an image instead of the actual image.
An embedding needs less words. You can embed individual words, phrases, like a whole prompt and longer paragraphs. You don't need 1024 words for a text embed. For example a famous library is called Sentence BERT (sbert).
When you embed images on the other hand, you cut them up into little squares on the tune of 32x32 px, and embeds one of them separately. chatGPT uses something like 250 tokens for smaller images. So a smaller image costs about as much as 200 words if represented graphically, and maybe much less words if you embed a text description of it.
Re: Vision language models are blind
#54Entertaining, but I think the conclusion is way off. > their vision is, at best, like that of a person with myopia seeing fine details as blurry is a crazy thing to write in an abstract. Did they try to probe that hypothesis at all? I could (well actually I can't) share some examples from my job of GPT-4v doing some pretty difficult fine-grained visual tasks that invalidate this. Personally, I rate this paper [1], wh…
There are quite a few "ai apologists" in the comments but I think the title is fair when these models are marketed towards low vision people ("Be my eyes" https://www.youtube.com/watch?v=Zq710AKC1gg ) as the equivalent to human vision. These models are implied to be human level equivalents when they are not. This paper demonstrates that there are still some major gaps where simple problems confound the models in unex…
Yea, really if you look at human learning/seeing/acting there is a feedback loop that LLM for example isn't able to complete and train on.
You see an object. First you have to learn how to control all your body functions to move toward it and grasp it. This teaches you about the 3 dimensional world and things like gravity. You may not know the terms, but it is baked in your learning model. After you get an object you start building a classification list "hot", "sharp", "soft and fuzzy", "tasty", "slick". Your learning model builds up a list of properties of objects and "expected" properties of objects.
Once you have this 'database' you create as a human, you can apply the logic to achieve tasks. "Walk 10 feet forward, but avoid the sharp glass just to the left". You have to have spatial awareness, object awareness, and prediction ability.
Models 'kind of' have this, but its seemingly haphazard, kind of like a child that doesn't know how to put all the pieces together yet. I think a lot of embodied robot testing where the embodied model feeds back training to the LLM/vision model will have to occur before this is even somewhat close to reliable.
Re: Vision language models are blind
#55I wonder how they would score if they used all 4 models and took a majority vote...?
Re: Vision language models are blind
#56Earlier quoted context omitted.
I don't see how this is "embarrassing" in the slightest. These models are not human brains, and the fact that people equate them with human brains is an embarrassing failure of the humans more than anything about the models. It's entirely unsurprising that there are numerous cases that these models can't handle that are "obvious to humans." Machine learning has had this property since its invention and it's a classic…
It is embarrassingly, shockingly bad, because these models are advertised and sold as being capable of understanding images. Evidently, all these models still fall short.
Humans are also shockingly bad on these tasks. And guess where the labeling was coming from…
Re: Vision language models are blind
#57Are the "random-baseline accuracy" numbers correct? In the "Two circles" test, do they really have 50% chance of overlapping? I think this comes from "Distances between circle perimeters: -0.15 to 0.5 times the diameter" but doesn't say the distribution they use.
They asked the AI a question with a yes/no response. If the AI chose randomly, it would be correct 50% of the time. That’s what “random baseline accuracy” means.
Re: Vision language models are blind
#58The title for this page and argument should be qualified with the specific generation of tools.
That's in the abstract, but, it's bad to not be specific. In this case, because current public-facing models are WIWEB: the worst it will ever be.
And there are trillion-dollar prizes at stake, so, improvement is happening as quickly as it possibly can.
Re: Vision language models are blind
#59Hugged to death from my perspective. Here is a backup: https://archive.ph/kOE3Q
Re: Vision language models are blind
#60Earlier quoted context omitted.
It is embarrassingly, shockingly bad, because these models are advertised and sold as being capable of understanding images. Evidently, all these models still fall short.
Not only are they capable of understanding images(the kind people might actually feed into such a system - photographs), but they're pretty good at it. A modern robot would struggle to fold socks and put them in a drawer, but they're great at making cars.
I mean, with some of the recent demos, robots have got a lot better at folding stuff and putting it up. Not saying it's anywhere close to human level, but it has taken a pretty massive leap from being a joke just a few years ago.