search

FengheTan9 / Multi-Level-Global-Context-Cross-Consistency

Official Pytorch Code base for "Multi-Level Global Context Cross Consistency Model for Semi-Supervised Ultrasound Image Segmentation with Diffusion Model"
MIT License
33 stars 1 forks source link

about test model #6

Closed Minami77 closed 1 year ago

Minami77 commented 1 year ago

Hi Thanks for sharing!

I found the test model(UNet) you used contians ConvMixer layer in your paper. But in the Evaluation Metrics and Comparison Methods section of your paper, you mentioned "all methods utilize U-Net as the backbone". Does this mean the UNet for all comparison methods contians ConvMixer layer?

FengheTan9 commented 1 year ago

Thanks for using our code. All methods use U-Net for backbones, including encoders and decoders with skip-connections. And the ConvMixer module is a part of our proposed method (ie. MGCC), and the backbones (ie. U-Net) of other methods do not include ConvMixer.

FengheTan9 commented 1 year ago

Well, ConvMixer is part of our SSL strategy for extract multi-level global context. This is unique to our SSL method. And our strategy can be used on any encoder-decoder structure.

Minami77 commented 1 year ago

Thanks for your response！