Domain Separation Networks
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), pp. 343-351, 2016.
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 generali...More
PPT (Upload PPT)