Joseph Nelson: prediction

Transcript context

…fair enough, maybe just outside of fair, just the future of computer vision, right? Like you are very involved in the community. What's the talk of the town at CVPR? Both of you went, who's doing the most interesting work? It's a question for both of you. I think the trends we're seeing towards more zero shot capability for common examples will accelerate. I think Mutu modality, meaning using, you know, images in tandem with text for richer understanding or images and video in tandem with audio and other mixed media will be a continued acceleration trend. The way I kind of see the field continuing to progress, the problem statement of computer vision is making sense of visual input. And I think about the world as the things that need to be observed follow your traditional bell curve, where like things that most frequently exist out in the world are on the center of that bell curve. And then there's things that are less frequently occurring that are in those long tails. For example, you know, as back as like 2014, you have the Cocoa data set, which sets out to say, Hey, can we find 80 common objects in context, like silverware and fridge and these sorts of things. And we also conceptualized the challenge of computer vision in terms of breaking it down into individual task types, because that's like the tools we had for the day. So that's why, you know, you have the origination of classification, object detection, instant segmentation. And then as you see things continue to progress. You have models and things that need to observe areas in the long tails. And so if you think of the Cocoa dataset as the center of that bell curve, I think of like the long tails, like really edge case problems. Some of our customers like Rivian, for example, only Rivian knows what the inside of like a Rivian should look like as it's assembled and put together before it makes its way to a customer and they're making custom parts. Right? So how could a model you've been trained on the things that go inside the componentry of producing a vehicle and Andreesen, What's kind of happening with computer vision is you're seeing models that generalize in the middle of the bell curve push outward faster. That's where you see the advent of like open text models or the richness of understanding of multimodal models. To allow richer understanding without perhaps any training, or maybe just using pre training and applying it to a given problem. And then, there's like, you know, kind of like the messy middle in between those two, right? So like, Akila kind of talked about examples where SAM does well out of distribution, where like, it finds an octopus, even though there wasn't octopi in the training data. I showed an example where, like, screenshots, where Sam isn't yet super great at screenshots, so maybe that's, like, in the messy middle or in the longer tails for now. But what's going to happen is there needs to be systems of validating the point of view that I think about, like, tooling to also validate that models are doing what we want them to do, adapting to datasets that we want them to adapt to. And so there's a lot of things on a forward looking basis that allow propelling that expansion of generalizability. e doing what we want them to do, adapting to datasets that we want them to adapt to. And so there's a lot of things on a forward looking basis that allow propelling that expansion of generalizability. That's for open text problems. That's where scaling up of training, of dataset curation, continues to play a massive role. Something that's notable, I think, about SAM2 is it's, what, 57, 000 videos? 51,…

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