-
**Describe the solution you'd like**
It would be nice to have an option for self-training. Self-training is related to active learning but gets labels for queries based on its predictions instead of …
-
Hi, There maybe be some questions of the "visdac.py", can you check it plz.
-
你好,
这个模型可以被用于unsupervised domain adaptation for 3D segmentation吗?技术小白真心求教。
谢谢!
-
-
Thank you for sharing code!
I have a question about the function get_centers that computes the centers of clusters.
Did you forget to normalize features before multiply them per mask? Or simply th…
-
https://arxiv.org/pdf/1702.05464.pdf
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can i…
leo-p updated
7 years ago
-
I see that this benchmark network is from sec3.1 in the MMT paper. How is it trained? Does it require collaborative training?
GJTNB updated
3 years ago
-
Thanks for your share!
When i study your code, I found that you used the true gt_boxes of target domain at the training stage. This is unsupervised domain adaptation, I think you can't get the groun…
-
Hi,
Could you please add our new work into this list? The paper is about learning Disentangled Representations to realize domain adaptation.
You could find the paper here: https://arxiv.org/abs/…
-
```Without cell-specific features, another solution could be to use domain adaptation methods where the model trains on a source cell type and uses unsupervised feature extraction methods to predict o…