Deep Discriminative Learning for Unsupervised Domain Adaptation

TL;DR

This paper introduces DEDA, a discriminative approach that directly trains classifiers for unlabeled target domains, achieving state-of-the-art results in unsupervised domain adaptation for image classification and sentiment analysis.

Contribution

The paper proposes a novel discriminative learning method for unsupervised domain adaptation that directly trains classifiers on target domain data, outperforming existing indirect methods.

Findings

Achieved state-of-the-art results on image classification benchmarks.

Performed best on Amazon reviews sentiment classification dataset.

Effective in zero-shot domain adaptation scenarios.

Abstract

The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled target domain samples, the standard approach is to learn a common representation for both source and target domain, thereby indirectly addressing the problem of learning a classifier in the target domain. However, such an approach does not address the task of classification in the target domain directly. In contrast, we propose an approach that directly addresses the problem of learning a classifier in the unlabeled target domain. In particular, we train a classifier to correctly classify the training samples while simultaneously classifying the samples in the target domain in an unsupervised manner. The corresponding model is referred to as Discriminative Encoding for Domain Adaptation (DEDA). We show that this simple approach for performing unsupervised domain adaptation is indeed quite powerful. Our method achieves state of the art results in unsupervised adaptation tasks on various image classification benchmarks. We also obtained state of the art performance on domain adaptation in Amazon reviews sentiment classification dataset. We perform additional experiments when the source data has less labeled examples and also on zero-shot domain adaptation task where no target domain samples are used for training.