Settings

Theme

EfficientSAM

yformer.github.io

57 points by Thomashuet 2 years ago · 7 comments

Reader

skadamat 2 years ago

Excited to play with this more! Forked the repo and added the models into the repo itself (migrated from Dropbox): https://github.com/xetdata/EfficientSAM

IshanMi 2 years ago

So if I'm understanding this correctly:

The SAM paper from this past April (that let you do zero-shot segmentation on any image, seemingly better than even OpenAI's CLIP) was using a ~600M parameter ViT model to generate image embeddings. And in order to make it less computationally expensive to generate those same embeddings, they replace that model with a smaller ViT encoder that was pre-trained using the masked auto-encoder back propagation method?

GaggiX 2 years ago

https://github.com/ChaoningZhang/MobileSAM was the previous attempt at reducing the size of the large image encoder used by SAM.

cchance 2 years ago

it's called efficient Sam and it appears to be onpar or better than fastsam but did I miss a memory or speed comparison?

  • yorwba 2 years ago

    The comparison is figure 1 of the paper. I think the bubble size represents number of parameters, which likely roughly corresponds to memory consumption.

naveen99 2 years ago

can’t wait for everywhere all at once function.

ShadowBanThis01 2 years ago

Is what?

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection