qqlu / Entity

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
Other
692 stars 58 forks source link

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation (ECCV2022) #31

Closed leichaoyang closed 6 months ago

leichaoyang commented 11 months ago

Where can I find the code of the CA-SSL?

qqlu commented 11 months ago

Hello,

You can directly use the existing entity segmentation model to generate entity masks. For example, directly use the CropFormer Visualization code. https://github.com/qqlu/Entity/blob/main/Entityv2/CODE.md.

This could be directly used for pseudo labels.

We will release the pseudo labels on 1,700,000 open images soon.

leichaoyang commented 11 months ago

Can you send me the code of CA-SSL? I want to learn the framework of the CA-SSL.

qqlu commented 11 months ago

Sorry, I do not understand your requirements.

The CA-SSL mainly uses the unlabeled data and its class-agnostic pesudo labels to warm-up the network whatever the framework be used.

leichaoyang commented 11 months ago

Thank you, I understand the idea of the paper.