search

LUSSeg / ImageNet-S

(TPAMI2022) The ImageNet-S benchmark/method for large-scale unsupervised/semi-supervised semantic segmentation.
165 stars 11 forks source link

Download benchmarking segmentation results #5

Closed Michaelsqj closed 1 year ago

Michaelsqj commented 2 years ago

Hi there,

Thank you for sharing the amazing work. I'm interested in extracting out the objects in imagenet for our own project. May I ask is there any way to download the best segmentation results using the method mentioned in your paper? Or do you suggest any other methods that has done the segmentation on imagenet, either supervised or unsupervised.

gasvn commented 2 years ago

Thanks for your interest in our work. We will open source a semi-supervised codebase and pretrained model in one or two weeks. It can achieve the best performance so far. You can infer the segmentation mask by then. Please let me know if you have any other questions.

gasvn commented 2 years ago

The code is now released on https://github.com/LUSSeg/ImageNetSegModel

Michaelsqj commented 2 years ago

Thank you very much! It's very helpful!