Skip to content

SichangHe/pennmlr--WebSAM-Adapter

 
 

Repository files navigation

WebSAM-Adapter

Authors

Alok Shah, Roberto Ligeralde, Gaurav Goel, Paul Loh

An implementation of WebSAM-Adapter from Ren et al.

Model Architecture

model_architecture

The adapter consists of 3 parts: Edge-Component Tuning, Patch-Embedding Tuning, and k adapter units. The EC and PE Tunes are learned linear layers applied to the Sobel-Filtered input image and the encoded patches respectively, with the i-th adapter unit using an MLP to feed the results to the i-th block of SAM's image encoder.

Training

We train the model on Webis-WebSeg-20, a dataset of 8,490 web page images with 42,450 ground truth segmentations.

About

an implementation of WebSam-Adapter: https://link.springer.com/chapter/10.1007/978-3-031-56027-9_27

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 73.2%
  • HTML 25.9%
  • Shell 0.9%