Conditional Adversarial Domain Adaptation

TL;DR

This paper introduces conditional adversarial domain adaptation, a framework that improves domain transferability by conditioning adversarial models on classifier predictions, achieving state-of-the-art results across multiple datasets.

Contribution

It proposes a novel conditional adversarial domain adaptation framework with two strategies: multilinear and entropy conditioning, enhancing transferability and discriminability.

Findings

Outperforms previous methods on five datasets.

Introduces two novel conditioning strategies.

Achieves theoretical guarantees and simplicity in implementation.

Abstract

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal distributions native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the cross-covariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. With theoretical guarantees and a few lines of codes, the approach has exceeded state-of-the-art results on five datasets.