Roboflow, every mention

27 scenes, the whole family · ← back to Roboflow

mentionsepisodesper episode tap a year for its mentions

Verbatim, from the transcripts: the passages where Roboflow comes up

loading…

▶ 1:03:45 Nader Khalil I was talking to Joseph, uh, from Roboflow, and, uh, your partner in crime.
▶ 1:22:58 Nader Khalil Uh, and so it was really exciting because, like, rovoflow, uh, I think, um, uh, I forgot.

▶ 0:03 unnamed speaker Okay, we're here in the remote studio with the grand return of the Roboflow and Latent Space and SAM combo. 4 times in the scene
▶ 14:20 Joseph Nelson And we pulled some of the updated stats on how impactful SAM is being across the RoboFlow community. 5 times in the scene
▶ 49:58 Nikhila Ravi I think also in many video use cases, I think, because if you were sharing on RoboFlow,
▶ 50:09 Nikhila Ravi So in, in some cases this, maybe it's, this isn't required to preserve the identities throughout the video and you just want to essentially do detection per frame, like for the RoboFlow Rapid examples you were sharing.
▶ 59:07 unnamed speaker RoboFlo can do that for you.
▶ 1:04:00 Joseph Nelson And so we've actually made a bet on SAM-III being a core part of auto-label at Roboflow, giving users a first pass of saying, hey, if you have a new image or you have a new video, start providing just a text prompt and allow SAM-III 2 times in the scene
▶ 1:05:53 Joseph Nelson And we called it, we called it rapid, but basically it's like, there's probably a model that already understands the objects in the world that you want to see.
▶ 1:12:09 unnamed speaker Uh, you know, I think, you know, we, we, we've sort of given a good overview and people obviously should read the paper and try out the playground, try out RoboFlow. 3 times in the scene

▶ 56:32 unnamed speaker Was there and did the, with Joseph from Roboflow that did like the prompt battle thing, like Harrison was a judge and it's like Jerry from Lama Index was there, like kind of like everybody that, uh, is kind of now breaking out.

▶ 0:07 Isaac Robinson Hi, we're Isaac and Peter from Roboflow, and we're going to talk about the best papers of 20, 24 in computer vision.
▶ 8:00 Isaac Robinson So, we at RoboFlow allow users to label data and train models on that data.
▶ 14:48 Isaac Robinson The next trend I'm interested in talking about is this interesting at Roboflow, we're super interested in training real time object detectors. 2 times in the scene
▶ 20:04 Isaac Robinson We also want to see people benchmarking an RF 100 more because that type of data is what's relevant for most users.
▶ 31:10 Peter Robicheaux Text datasets on RoboFlow, and you can train a Florence II model, and you can actually train a Polygema II model on RoboFlow, which we got into the platform within, like, 14 hours of release, which I was really excited about. 2 times in the scene
▶ 38:17 Peter Robicheaux And so I think that this benchmark doesn't do a great job of selling how good of a pre-trained model MV-II is, and we would like to see, uh, performance on fewer data as examples and not trained to convergence on object detection, so…

▶ 34:12 unnamed speaker Uh, yeah, these guys, uh, Nikki is a friend, um, and Roboflow is a very different friend of ours.

▶ 5:10 Joseph Nelson So at RoboFlow, we were very quick to enable the community of computer vision developers and engineers to use SAM and apply it to their problems. 4 times in the scene
▶ 20:42 Joseph Nelson So in the SAM one demo, the way that it was structured, and also this is the way that we have our SAM tool structured in RoboFlow as well.
▶ 23:40 Shawn Wang I want to talk about more about things from the paper, but I think we're still in this sort of demo section, and so I want to hand it to Joseph for his demo to see what the RoboFlow site looks like.
▶ 32:36 Joseph Nelson One benchmark that we introduced at CBPR is this thing called RF 100, which is like seven different domain type problems that the industry commonly is working on in vision, like underwater, document processing, aerial examples, medicine…
▶ 39:09 Joseph Nelson We joked that when SAM-ONE came out at Roboflow, we're like, was this purpose-built for our software?
▶ 57:43 Joseph Nelson We hosted this, uh, challenge at CBPR when we introduced RF 100, which is kind of meant to be the anti-COCO. 2 times in the scene

▶ 54:02 unnamed speaker Um, I know, I think Sean, you put in a question from Joseph here in the show notes, our friend Joseph Nelson, founder of RoboFlow and Office, um, co, co-worker, I guess.

▶ 53:03 unnamed speaker I could use this for this, and then they build out something, and maybe they don't use, open it, GPT-IV-V, they use Roboflow or whatever else.

Turn any episode into a week of clips.