about DA usage scenario

[liangzimei]

Hi, it‘’s my first time to try domain adaptation. Here is my scenario: i am doing a image classification task, there are already 100k training data with labels (called A), i also can obtain large data with no labels (called B) . Data A and B's domain shift are small. The plan i choose now is using data A to train a model to predict B's data directly. the results is also good. when i annotating more data from B, and use them and data A together to train, the results are better. However, to reduce the work of annotating images, my question is can i treat A as source, B as target to improve accuracy further (i.e., adding more data B in training phase compared with current plan) .

[caozhangjie]

Yes, you can. But add more annotated data is usually better than using unsupervised target domain with domain adaptation. But if you use domain adaptation, you only need to annotate a little data to achieve comparable performance.

[liangzimei]

thanks @caozhangjie , is there any good semi-supervised DA methods to suggest? ( i find that most of DA are unsupervised