EfficientSAM
yformer.github.io
EfficientSAM
1–8 of 8 posts
Re: EfficientSAM
#2can’t wait for everywhere all at once function.
Re: EfficientSAM
#3https://github.com/ChaoningZhang/MobileSAM was the previous attempt at reducing the size of the large image encoder used by SAM.
Re: EfficientSAM
#4it's called efficient Sam and it appears to be onpar or better than fastsam but did I miss a memory or speed comparison?
Re: EfficientSAM
#5it's called efficient Sam and it appears to be onpar or better than fastsam but did I miss a memory or speed comparison?
The comparison is figure 1 of the paper. I think the bubble size represents number of parameters, which likely roughly corresponds to memory consumption.
Re: EfficientSAM
#6Excited to play with this more! Forked the repo and added the models into the repo itself (migrated from Dropbox): https://github.com/xetdata/EfficientSAM
Re: EfficientSAM
#7Is what?
Re: EfficientSAM
#8So 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?