Domain Separation Networks

The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data where annotations are provided automatically. Despite their appeal, such models often fail to generalize from synthetic to real images, necessitating domain adaptation algorithms to manipulate these models before they can be successfully applied. Existing approaches focus either on mapping representations from one domain to the other, or on learning to extract features that are invariant to the domain from which they were extracted. However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain. We suggest that explicitly modeling what is unique to each domain can improve a model's ability to extract domain-invariant features. Inspired by work on private-shared component analysis, we explicitly learn to extract image representations that are partitioned into two subspaces: one component which is private to each domain and one which is shared across domains. Our model is trained not only to perform the task we care about in the source domain, but also to use the partitioned representation to reconstruct the images from both domains. Our novel architecture results in a model that outperforms the state-of-the-art on a range of unsupervised domain adaptation scenarios and additionally produces visualizations of the private and shared representations enabling interpretation of the domain adaptation process.

PDF Abstract NeurIPS 2016 PDF NeurIPS 2016 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Domain Adaptation MNIST-to-MNIST-M DSN (DANN) Accuracy 83.2 # 3
Domain Generalization PACS DSN (Alexnet) Average Accuracy 67.37 # 113
Domain Adaptation SVNH-to-MNIST DSN (DANN) Accuracy 82.7 # 7
Domain Adaptation Synth Digits-to-SVHN DSN (DANN) Accuracy 91.2 # 1
Domain Adaptation Synth Objects-to-LINEMOD DSN (DANN) Classification Accuracy 100 # 1
Mean Angle Error 53.27 # 1
Domain Adaptation Synth Signs-to-GTSRB DSN (DANN) Accuracy 93.1 # 2


No methods listed for this paper. Add relevant methods here