Unsupervised Domain Adaptation by Backpropagation

09/26/2014 ∙ by Yaroslav Ganin, et al. ∙ 0

Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different domain (e.g. synthetic images) are available. Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of "deep" features that are (i) discriminative for the main learning task on the source domain and (ii) invariant with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a simple new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation. Overall, the approach can be implemented with little effort using any of the deep-learning packages. The method performs very well in a series of image classification experiments, achieving adaptation effect in the presence of big domain shifts and outperforming previous state-of-the-art on Office datasets.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

page 10

Code Repositories

transfer-learning

an attempt to use arXiv:1409.7495 in data from https://www.kaggle.com/c/flavours-of-physics


view repo

MIT-6.864-Question-Retrieval-and-Transfer-Learning

None


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.