Preprint
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Learning descriptors for object recognition and 3D pose estimation2015
- Beyond the shortest path: Unsupervised domain adaptation by Sampling Subspaces along the Spline Flow2015
- Evaluation of Traffic Sign Recognition Methods Trained on Synthetically Generated Data2013
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012
- Geodesic flow kernel for unsupervised domain adaptation2012
- Domain adaptation for object recognition: An unsupervised approach2011
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- A theory of learning from different domainsMachine Learning, 2009
- Metrics for 3D Rotations: Comparison and AnalysisJournal of Mathematical Imaging and Vision, 2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998