Unsupervised Domain Adaptation by Backpropagation

by   Yaroslav Ganin, et al.

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.


page 6

page 10


Domain-Adversarial Training of Neural Networks

We introduce a new representation learning approach for domain adaptatio...

Simplified Neural Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) is the task of modifying a statisti...

Weak Adaptation Learning – Addressing Cross-domain Data Insufficiency with Weak Annotator

Data quantity and quality are crucial factors for data-driven learning m...

Weakly-supervised Caricature Face Parsing through Domain Adaptation

A caricature is an artistic form of a person's picture in which certain ...

Private Domain Adaptation from a Public Source

A key problem in a variety of applications is that of domain adaptation ...

Image to Video Domain Adaptation Using Web Supervision

Training deep neural networks typically requires large amounts of labele...

PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models

Pivot-based neural representation models have lead to significant progre...

Code Repositories


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

view repo



view repo