Geodesy

Benchmark (surveying)

Transfer of learning

Statistics

Feature learning

Theoretical computer science

Operating system

Parallel computing

Computer science

Outlier

Transfer (computing)

Mathematics

Geography

Domain (mathematical analysis)

Mathematical analysis

Artificial intelligence

Matching (statistics)

Subspace topology

Space (punctuation)

Machine learning

Adversarial system

Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. Existing domain adversarial networks assume fully shared label space across domains. In the presence of big data, there is strong motivation of transferring both classification and representation models from existing large-scale domains to unknown small-scale domains. This paper introduces partial transfer learning, which relaxes the shared label space assumption to that the target label space is only a subspace of the source label space. Previous methods typically match the whole source domain to the target domain, which are prone to negative transfer for the partial transfer problem. We present Selective Adversarial Network (SAN), which simultaneously circumvents negative transfer by selecting out the outlier source classes and promotes positive transfer by maximally matching the data distributions in the shared label space. Experiments demonstrate that our models exceed state-of-the-art results for partial transfer learning tasks on several benchmark datasets.

Partial Transfer Learning with Selective Adversarial Networks