Domain-Adversarial Training of Neural Networks

by   Yaroslav Ganin, et al.

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains. The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate 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 new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation and stochastic gradient descent, and can thus be implemented with little effort using any of the deep learning packages. We demonstrate the success of our approach for two distinct classification problems (document sentiment analysis and image classification), where state-of-the-art domain adaptation performance on standard benchmarks is achieved. We also validate the approach for descriptor learning task in the context of person re-identification application.


page 14

page 21

page 27


Unsupervised Domain Adaptation by Backpropagation

Top-performing deep architectures are trained on massive amounts of labe...

Domain-Adversarial Neural Networks

We introduce a new representation learning algorithm suited to the conte...

Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

While domain adaptation has been actively researched in recent years, mo...

Deep Transfer Learning with Joint Adaptation Networks

Deep networks have been successfully applied to learn transferable featu...

Gradient Regularized Contrastive Learning for Continual Domain Adaptation

Human beings can quickly adapt to environmental changes by leveraging le...

Diversity-Based Generalization for Neural Unsupervised Text Classification under Domain Shift

Domain adaptation approaches seek to learn from a source domain and gene...

Gated Convolutional Neural Networks for Domain Adaptation

Domain Adaptation explores the idea of how to maximize performance on a ...

Please sign up or login with your details

Forgot password? Click here to reset