SRDC-CVPR2020
SRDC-CVPR2020 copied to clipboard
Code release for Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering (CVPR2020-Oral).
I am trying to run the model on a custom dataset, which is significantly larger than the datasets used in this repo. On line 520 of trainer.py while calculating k_means,...
@huitangtang thanks for your excellent work! When I download office31 from your link, I find it does not contain the folder of webcam_half dslr_half and amazon_half. Can you tell me...
I failed to reproduce the experimental results in your paper. For example, on the A-W dataset of office31, the best result is only 92.70. I used the default hyperparameters, and...
Line 294 of the file "trainer.py" unpacks input, target, and index from the val_loader_target. Could you explain or give an example of what the index indicates? Because generally we always...
Thanks for sharing the code. I have a question. In the TarDisClusterLoss, why is the true label of the target used in the 141 line?
License
Hi, may I know what license this code repo falls into? Thank you very much.
Hello, thanks for checking this issue. I use the uploaded code and run UDA on the Office-Home dataset. However, I cannot reproduce the claimed results in the paper. Some of...