Importance Weighted Adversarial Nets for Partial Domain Adaptation

TL;DR

This paper introduces an importance weighted adversarial network approach tailored for partial domain adaptation, effectively handling scenarios where the target domain has fewer classes than the source, by identifying outlier classes and aligning shared class distributions.

Contribution

It extends adversarial domain adaptation methods to partial settings, incorporating importance weighting to distinguish outlier classes and improve transfer learning.

Findings

Successfully identifies outlier classes in source data.

Reduces distribution shift for shared classes.

Improves adaptation performance in partial domain scenarios.

Abstract

This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the source domain. Previous domain adaptation methods generally assume the identical label spaces, such that reducing the distribution divergence leads to feasible knowledge transfer. However, such an assumption is no longer valid in a more realistic scenario that requires adaptation from a larger and more diverse source domain to a smaller target domain with less number of classes. This paper extends the adversarial nets-based domain adaptation and proposes a novel adversarial nets-based partial domain adaptation method to identify the source samples that are potentially from the outlier classes and, at the same time, reduce the shift of shared classes between domains.