Domain-Adversarial Training of Neural Networks

Unsupervised domain adaptation with gradient reversal

Released in: Domain-Adversarial Training of Neural Networks

Contributor:

Summary

The authors introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. This 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. The authors demonstrate the success of the proposed 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, and also validate the approach for descriptor learning task in the context of person re-identification.

2016

Year Released

Key Links & Stats

Domain-Adversarial Training of Neural Networks

ML Tasks

  1. General
  2. Domain Adaptation

ML Platform

  1. Not Applicable

Modalities

  1. General

Verticals

  1. General

CG Platform

  1. Not Applicable

Related organizations

Skoltech

Universite Laval

Universite de Sherbrooke