Peter Robicheaux: prediction

Transcript context

…like, You're asking for it to segment these two classes of objects, and then it finds, like, their locations using these tokens, and it finds their masks using some encoding of the masks into tokens. And, yeah, so, one of my critiques, I guess, of PolyGemma 1, at least, is that You find that performance saturates as a pre trained model after only 300 million examples seen. So, what this graph is representing is each blue dot is a performance on some downstream task. And you can see that after seeing 300 million examples, It sort of does equally well on all of the downtrend tasks that they tried it on, which was a lot as 1 billion examples, which to me also kind of suggests a lack of capacity for this model. PolyGemma2, [00:32:00] you can see the results on object detection. So these were transferred to to Coco. And you can see that this sort of also points to an increase in capacity being helpful to the model. You can see as. Both the resolution increases, and the parameter count of the language model increases, performance increases. So resolution makes sense, obviously, it helps to find small images, or small objects in the image. But it also makes sense for another reason, which is that it kind of gives the model a thinking register, and it gives it more tokens to, like, process when making its predictions. But yeah, you could, you could say, oh, 43. 6, that's not that great, like Florence 2 got 60. But this is not Training a dino or a debtor on top of this language or this image encoder. It's doing the raw language modeling task on Cocoa. So it doesn't have any of the bells and whistles. It doesn't have any of the fancy losses. It doesn't even have bipartite graph matching or anything like that. Okay, the big result and one of the reasons that I was really excited about this paper is that they blow everything else away [00:33:00] on MMVP. I mean, 47. 3, sure, that's nowhere near human accuracy, which, again, is 94%, but for a, you know, a 2 billion language, 2 billion parameter language model to be chat2BT, that's quite the achievement. And that sort of brings us to our final pick for paper of the year, which is AIMV2. So, AIMV2 sort of says, okay, Maybe this language model, like, maybe coming up with all these specific annotations to find features and with high fidelity and pixel space isn't actually necessary. And we can come up with an even simpler, more beautiful idea for combining you know, image tokens and pixel tokens in a way that's interfaceable for language tasks. And this is nice because it can scale, you can come up with lots more data if you don't have to come up with all these annotations, right? So the way that it works. is it does something very, very similar to PolyGemo, where you have a vision encoder that dumps image tokens into a decoder only transformer. But [00:34:00] the interesting thing is that it also autoregressively tries to learn the mean squared error of the image tokens. So instead of having to come up with fancy object detection or semantic, or segment, or segmentation labels, you can just try to reconstruct the image and have it learn fine grained features that way. So instead of having to come up with fancy object detection or semantic, or segment, or segmentation labels, you can just try to reconstruct the image and have it learn fine grained features that way. And it does this in kind of, I think, a beautiful way that's kind of compatible with the PolyGemma line of thinking, which is randomly sampling a prefix line of thinking Prefix length and using only this number of image tokens as the prefix. And so doing a similar thing with the causal. So the causal with prefix is the, the attention mask on the right. So it's doing full block attention with some randomly sampled number of image tokens to then reconstruct the rest of the image and the downstream caption for that image. And so, This is the dataset that they train on. It's image or internet scale data, very high quality data created by the data filtering networks paper, essentially which is maybe The best clip data that exists. [00:35:00] And we can see that this is finally a model that doesn't saturate. It's even at the highest parameter count, it's, it appears to be, oh, at the highest parameter account, it appears to be improving in performance with more and more samples seen. And so you can sort of think that. You know, if we just keep bumping the parameter count and increasing the example scene, which is the, the, the line of thinking for language models, then it'll keep getting better. So how does it actually do at finding, oh, it also improves with resolution, which you would expect for a model that This is the ImageNet classification accuracy, but yeah, it does better if you increase the resolution, which means that it's actually leveraging and finding fine grained visual features. And so how does that actually do compared to CLIP on Cocoa? Well, you can see that if you slap a transformer detection head on it, Entry now in Cocoa, it's just 60. 2, which is also within spitting distance of Soda, which means that it does a very good job of [00:36:00] finding visual features, but you could say, okay, well, wait a second. Clip got to 59. 1, so. Like, how does this prove your claim at all? Because doesn't that mean like clip, which is known to be clip blind and do badly on MMVP, it's able to achieve a very high performance on fine, on this fine grained visual features task of object detection, well, they train on like, Tons of data. They train on like objects, 365, Cocoa, Flickr and everything else. And so I think that this benchmark doesn't do a great job of selling how good of a pre trained model MV2 is. And we would like to see the performance on fewer data as examples and not trained to convergence on object detection. So seeing it in the real world on like a dataset, like RoboFlow 100, I think would be quite interesting. And our, our, I guess our final, final pick for paper of 2024 would be Moondream. So introducing Vic to talk about that. But overall, that was exactly what I was looking for. Like best of 2024, an amazing job. Yeah, you can, [00:37:00] if there's any other questions while Vic gets set up, like vision stuff, yeah, Vic, go ahead. Hi,…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.