Earlier quoted context omitted.
YOLO is not a segmentation model.
https://docs.ultralytics.com/tasks/segment/
Thanks! TIL there's a class of segmentation models with the YOLO naming scheme.
Meta Segment Anything Model 3
11–20 of 50 posts
Re: Meta Segment Anything Model 3
#12Side question: what are the current top goto open models for image captioning and building image embeddings dbs, with somewhat reasonable hardware requirements?
I would suggest YOLO. Depending on your domain, you might also finetune these models. Its relativly easy as they are not big LLMs but either image classification or bounding boxes.
I would recommend bounding boxes.
Re: Meta Segment Anything Model 3
#13Side question: what are the current top goto open models for image captioning and building image embeddings dbs, with somewhat reasonable hardware requirements?
I would suggest YOLO. Depending on your domain, you might also finetune these models. Its relativly easy as they are not big LLMs but either image classification or bounding boxes. I would recommend bounding boxes.
Which YOLO?
Re: Meta Segment Anything Model 3
#14Released last week. Looks like all the weights are now out and published. Don’t sleep on the SAM 3D series — it’s seriously impressive. They have a human pose model which actually rigs and keeps multiple humans in a scene with objects, all from one 2D photo (!), and their straight object 3D model is by far the best I’ve played with - it got a really very good lamp with translucency and woven gems in usable shape in under 15 seconds.
Re: Meta Segment Anything Model 3
#15I do a test on multimodal LLMs where I show them a dog with 5 legs, and ask them to count how many legs the dog has. So far none of them can do it. They all say "4 legs". Segment anything however was able to segment all 5 dog legs when prompted to. Which means that meta is doing something else under the hood here, and may lend itself to a very powerful future LLM. Right now some of the biggest complaints people have…
You don’t need segmentation to count legs. Object detection can do that. DeepLabCut from 2020 perhaps.
Re: Meta Segment Anything Model 3
#16Earlier quoted context omitted.
I would suggest YOLO. Depending on your domain, you might also finetune these models. Its relativly easy as they are not big LLMs but either image classification or bounding boxes. I would recommend bounding boxes.
Which YOLO?
Any current one. they are easy to use and you can just benchmark them yourself.
I'm using small and medum.
Also the code for using it is very short and easy to use. You can also use ChatGPT to generate small exepriments to see what fits your case better
Re: Meta Segment Anything Model 3
#17Released last week. Looks like all the weights are now out and published. Don’t sleep on the SAM 3D series — it’s seriously impressive. They have a human pose model which actually rigs and keeps multiple humans in a scene with objects, all from one 2D photo (!), and their straight object 3D model is by far the best I’ve played with - it got a really very good lamp with translucency and woven gems in usable shape in u…
https://ai.meta.com/blog/sam-3d/ for those interested.
Re: Meta Segment Anything Model 3
#18Earlier quoted context omitted.
Which YOLO?
Any current one. they are easy to use and you can just benchmark them yourself. I'm using small and medum. Also the code for using it is very short and easy to use. You can also use ChatGPT to generate small exepriments to see what fits your case better
There aren’t any YOLO models for captioning and the other models aren’t robust enough to make for good embedding models.
Re: Meta Segment Anything Model 3
#19Which (if any) of these models could run on a RaspberryPi for object recognition at several FPS?
Re: Meta Segment Anything Model 3
#20Surprisingly, SAM3 works bad on engineering drawings while SAM2 kinda works, and VLMs like Qwen3-VL works as well