Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

SAM 2: Segment Anything in Images and Videos

github.com

Post reply on HN
Print view View original

141–150 of 159 posts

Re: SAM 2: Segment Anything in Images and Videos

#141

Post by Zuiii »

Nesco wrote: post #28
robbomacrae wrote: post #4

Earlier quoted context omitted.

Code, model, data and under Apache 2.0. Impressive. Curious how this was allowed to be more open source compared to Llama's interesting new take on "open source". Are other projects restricted in some form due to technical/legal issues and the desire is to be more like this project? Or was there an initiative to break the mold this time round?

LLMs are trained on the entire internet so loads of copyrighted data, which Meta can’t distribute, and is afraid to even reference

This argument doesn't make sense to me unless you're talking about the training material. If that is not the case, then how does this argument relate to the license Meta attempts to force on downloaders of LLaMa weights?

Re: SAM 2: Segment Anything in Images and Videos

#142

Post by dyauspitr »

sashank_1509 wrote: post #75
rkagerer wrote: post #53

Earlier quoted context omitted.

I guess the demo simply doesn't work unless you accept cookies?

Are there people who don’t accept cookies? Don’t most websites require you to accept cookies?

I never accept any they don’t force me to accept.

Re: SAM 2: Segment Anything in Images and Videos

#143

Post by sintezcs »

jonnyscholes wrote: post #116
nullandvoid wrote: post #113

Anyone have any home project ideas (or past work) to apply this to / inspire others? I was initially thinking the obvious case would be some sort of system for monitoring your plant health. It could check for shrinkage / growth, colour change etc and build some sort of monitoring tool / automated watering system off that.

I used the original SAM (alongside Grounding DINO) to create an ever growing database of all the individual objects I see as I go about my daily life. It automatically parses all the photos I take on my Meta Raybans and my phone along with all my laptop screenshots. I made it for an artwork that's exhibiting in Australia, and it will likely form the basis of many artworks to come. I haven't put it up on my website ye…

Wow, that’s really cool!

Re: SAM 2: Segment Anything in Images and Videos

#144

Post by NorwegianDude »

ipsum2 wrote: post #54
gpm wrote: post #36

> This research demo is not open to residents of, or those accessing the demo from, the States of Illinois or Texas. Alright, I'll bite, why not?

It's because their biometric privacy laws are written in such a general way that detecting the presence of a face is considered illegal.

So there will be a lot of blurry portraits coming from Illinois and Texas as autofocus can't find faces? /s

Re: SAM 2: Segment Anything in Images and Videos

#145

Post by DonHopkins »

nyxtom wrote: post #140
nravi20 wrote: post #2

Hi from the Segment Anything team! Today we’re releasing Segment Anything Model 2! It's the first unified model for real-time promptable object segmentation in images and videos! We're releasing the code, models, dataset, research paper and a demo! We're excited to see what everyone builds! https://ai.meta.com/blog/segment-anything-2/

Is there a reason Texans can't use the demo?

[flagged]

Re: SAM 2: Segment Anything in Images and Videos

#146

Post by Szpadel »

swyx wrote: post #23

i covered SAM 1 a year ago ( https://news.ycombinator.com/item?id=35558522 ). notes from quick read of the SAM 2 paper https://ai.meta.com/research/publications/sam-2-segment-anyt... 1. SAM 2 was trained on 256 A100 GPUs for 108 hours (SAM1 was 68 hrs on same cluster). Taking the upper end $2 A100 cost off gpulist means SAM2 cost ~$50k to train - surprisingly cheap for adding video understanding? 2. new dataset: the…

> 4. memory attention: SAM2 is a transformer with memory across frames! special "object pointer" tokens stored in a "memory bank" FIFO queue of recent and prompted frames. Has this been explored in language models? whoa?

interesting, how do you think this could be introduced to llm? I imagine in video some special tokens are preserved in input to next frame, so kind of like llms see previous messages in chat history, but it's filters out to only some category of tokens to limit size of context.

I believe this is trick already borrowed from llm into video space.

(I didn't read the paper, so that's speculation on my side)

Re: SAM 2: Segment Anything in Images and Videos

#147

Post by mike_hearn »

nyxtom wrote: post #140
nravi20 wrote: post #2

Hi from the Segment Anything team! Today we’re releasing Segment Anything Model 2! It's the first unified model for real-time promptable object segmentation in images and videos! We're releasing the code, models, dataset, research paper and a demo! We're excited to see what everyone builds! https://ai.meta.com/blog/segment-anything-2/

Is there a reason Texans can't use the demo?

Texas and Illinois. Both issued massive fines against Facebook for facial recognition, over a decade after FB first launched the feature. Segmentation is I guess usable to identify faces, so may seem too close to facial recognition to launch.

Basically the same issue the EU has with demos not launching there. You fine tech firms under vague laws often enough, and they stop doing business there.

Re: SAM 2: Segment Anything in Images and Videos

#149

Post by owenpalmer »

Zuiii wrote: post #141
Nesco wrote: post #28

Earlier quoted context omitted.

LLMs are trained on the entire internet so loads of copyrighted data, which Meta can’t distribute, and is afraid to even reference

This argument doesn't make sense to me unless you're talking about the training material. If that is not the case, then how does this argument relate to the license Meta attempts to force on downloaders of LLaMa weights?

they're literally talking about the training material.

Re: SAM 2: Segment Anything in Images and Videos

#150

Post by arendtio »

rkagerer wrote: post #53
minimaxir wrote: post #14

The web demo is actually pretty neat: https://sam2.metademolab.com/demo I selected each shoe as individual objects and the model was able to segment them even as they overlapped.

I guess the demo simply doesn't work unless you accept cookies?

I think under the GDPR this is even illegal.
Post reply on HN