Input for the unsupervised branch about cct HOT 2 CLOSED

Hi @saramsv
Thank you for your interest.

In a practical case, yes you are right, the unsupervised branch only takes the images without any labels. In our case, given that we only simulate the semi-supervised case by ignoring the labels of already labeled images, we do however load the labels, but they are only used to compute the acc and miou during for printing reasons only, they are not used in training.

In your case, you can create two datasets, one with labels for the supervised branch and any without any for the unsupervised branch. You'll also need to comment out the parts in trainer.py that use the labels of the unsupervised dataset (called target_ul) to compute the mIoU.

Hope I answered your question.

from cct.

Thank you so much for your prompt reply. Yes, that makes a lot of sense.

from cct.