search

SHI-Labs / Semi-Supervised-Transfer-Learning

[CVPR 2021] Adaptive Consistency Regularization for Semi-Supervised Transfer Learning
http://arxiv.org/abs/2103.02193
MIT License
101 stars 15 forks source link

MURA exprtiment questions #9

Open ricky-696 opened 8 months ago

ricky-696 commented 8 months ago

Hello, I'd like to inquire whether you employed different models for distinct parts when working with the MURA dataset or if a single model was used to predict all parts.

If multiple models were utilized, how were the 1000 and 400 images divided during the experiment?

Re-dot-art commented 5 months ago

Hello, I'd like to inquire whether you employed different models for distinct parts when working with the MURA dataset or if a single model was used to predict all parts.

If multiple models were utilized, how were the 1000 and 400 images divided during the experiment?

I think the same model should be used to train the data in the MURA dataset, only to distinguish whether there is a disease, that is, binary classification. The label images should be randomly selected from each type. Also, can you provide the usage code for the MURA dataset? I found that this part is not included in the open source code. Thank you!