Partial Transfer Learning with Selective Adversarial Networks

TL;DR

This paper introduces Selective Adversarial Network (SAN), a method for partial transfer learning that effectively handles the challenge of transferring knowledge when the target label space is a subset of the source, outperforming previous approaches.

Contribution

The paper proposes SAN, a novel adversarial network that selectively matches shared label spaces and excludes outlier classes, advancing partial transfer learning.

Findings

SAN outperforms state-of-the-art methods on benchmark datasets.

It effectively reduces negative transfer by selecting relevant source classes.

The approach improves transfer accuracy in partial label space scenarios.

Abstract

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 big domains to unknown small 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.