Domain Separation Networks

by   Konstantinos Bousmalis, et al.

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.


page 7

page 12

page 14


Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

Collecting well-annotated image datasets to train modern machine learnin...

Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition

Unsupervised domain adaptation of speech signal aims at adapting a well-...

Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach

Unsupervised domain adaptation (uDA) models focus on pairwise adaptation...

Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analy...

Unsupervised Wasserstein Distance Guided Domain Adaptation for 3D Multi-Domain Liver Segmentation

Deep neural networks have shown exceptional learning capability and gene...

Continuously Indexed Domain Adaptation

Existing domain adaptation focuses on transferring knowledge between dom...

Localising In Complex Scenes Using Balanced Adversarial Adaptation

Domain adaptation and generative modelling have collectively mitigated t...

Please sign up or login with your details

Forgot password? Click here to reset