Domain-adversarial training of neural networks

Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky

    Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

    107 Citations (Scopus)


    We introduce a 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 behavior 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 can thus be implemented with little effort using any of the deep learning packages. We demonstrate the success of our approach for 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.

    Original languageEnglish
    Title of host publicationAdvances in Computer Vision and Pattern Recognition
    PublisherSpringer London
    Number of pages21
    Publication statusPublished - 2017

    Publication series

    NameAdvances in Computer Vision and Pattern Recognition
    ISSN (Print)2191-6586
    ISSN (Electronic)2191-6594


    Dive into the research topics of 'Domain-adversarial training of neural networks'. Together they form a unique fingerprint.

    Cite this