-
The econml.metalearners.DomainAdaptationLearner does not have a `score` attribute. Is there a way to score it similar to CausalforestDML and DRL?
est.score()
-
Exampleにドメイン適応用の事例を作りたい。現状はドメイン汎化のみ。
具体的には、
pytransfer.trainer.pyの中に、ドメイン適応用のLearner(DALearner)を作るのと、データセットを読み込む部分を作れば良い、はず。
-
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 noticed that the method in the paper relies heavily on hyperparameter tuning. However, since the target domain lacks labels, tuning ultimately relies on validation set performance for optimal result…
-
1.Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop（2019）
collaborate regression-based (as initial pose) and iterative optimization-based approach.
code: No
2.Weakly S…
-
Hi, I'm very interested in your work, and what datastets do you use for this task?
-
Hi @antoinedemathelin ,
Thanks for the wonderful tool to experiment different methods.
In my use case, I have multiple source domains (with labelled examples) and multiple target domains (unlabelled…
-
https://arxiv.org/pdf/1607.03516.pdf
In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new m…
leo-p updated
7 years ago
-
Hello,
The front-end module is used in the paper "FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation". Do you know when the .prototxt files used in the paper will be made av…
-
Impressive work. Can' t wait to get the code. so when?!