Deep Transfer Learning with Joint Adaptation Networks

TL;DR

This paper introduces Joint Adaptation Networks (JAN), a deep transfer learning model that aligns joint distributions of multiple layers across domains using JMMD, achieving state-of-the-art results.

Contribution

JAN is the first to align joint distributions of multiple layers in deep networks for transfer learning, improving adaptation performance.

Findings

Achieves state-of-the-art results on standard datasets.

Effectively aligns joint distributions across domains.

Uses adversarial training with JMMD for domain adaptation.

Abstract

Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain. In this paper, we present joint adaptation networks (JAN), which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domains based on a joint maximum mean discrepancy (JMMD) criterion. Adversarial training strategy is adopted to maximize JMMD such that the distributions of the source and target domains are made more distinguishable. Learning can be performed by stochastic gradient descent with the gradients computed by back-propagation in linear-time. Experiments testify that our model yields state of the art results on standard datasets.