Joseph Nelson: prediction

Transcript context

…000 videos? About 51, 000, yeah. And 100, 000 internal datasets. That's, like, not Massive, right? And the model size also isn't, you know, the largest, largest model being a couple hundred million parameters. The smallest model is 38 million parameters and can run at 45 FPS on an A100, right? Like the capabilities of, we're going to see more capable, more generalizable models. Being able to run on a higher wide array of problems with zero or multi shot capability on a faster, a faster rate. And I think the architecture innovations and things like SAM2 of memory, of increasingly like transformers making their way into division and probably blended architectures increasingly too. So my viewpoint of like on a go forward basis is we will have that bell curve of what humans can see both in the center of that curve and the long tails. And architectural changes allow richer understanding, multi and zero shot, and putting those into systems and putting those into industry and putting those into contexts that allow using them in practical and pragmatic ways. Nicola, I'd love to hear like your thought and perspective of like how you think the research trends map or don't map to that. And like maybe some of the key innovations that you saw at CVPR this year that, you know, Got you excited about the direction and maybe some promising early directions that you're thinking about researching or pushing the boundaries of further. Yeah, I just wanted to actually reply to a couple of things that you said about so actually in video object segmentation, the number of classes. that are annotated in these, and then the size of these datasets are really small. So with SAM, it's, you know, we had a billion masks, we had 11 million images, didn't have class labels. But even before that, there were a lot of datasets that have class labels and are annotated. With significantly more with, with like a lot of class labels, whereas in video datasets, the number of class labels are very small. So there's like YouTube VOS, which has 94 object categories, there's Mose, which has around like 30 or so object categories. And they're usually like people, there's cars, there's dogs and cats and all these common objects, but not really, they don't really cover a very large number of object categories. And so while Sam learned this general notion of what an object is in an image. These video tracking models actually don't have that knowledge at all. And so that's why having this data set is really important for the segment anything capability in video because if you just provide the mask as the input to an off the shelf Video object segmentation model. It might not actually be able to track that arbitrary object mask as effectively as a SAM2 model that's actually trained to track. Any object across the entire video. So doing these sort of combining two models together to try to get a capability that will actually only get you so far and being able to actually create that the dataset to enable that anything capability, it was actually really important and we can actually see that when we do comparisons with baselines where we provide some two with the same input mask and the baseline model with the same input mask. For example, the t shirt of a person, SAM2 can track the t shirt effectively across the entire video, whereas these baselines might actually start tracking the entire person, because that's what they're used to doing, and isolating it to just one part of the person is not something they were ever trained to do, and so those are sort of some of the limitations. Another thing is, Segmenting an image and segmenting a video frame are actually two different things. So a video frame is still an image, but there might be motion blur, or it might have lower resolution. Or there's actually, we found that when, in the SAM2 paper, we have this study of where we look at the Sam image segmentation task on images and also on frames from videos. And we find that actually SAM2 is a lot better than SAM when it comes to segmenting objects in video frames. Because they actually have a sort of slightly different distribution than images. And so I think that's maybe one learning from this project, is like combining two models and sort of just smushing things together might not actually be as effective as if you really think about how to build things in a, in a unified way.…

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