DeepAI AI Chat
Log In Sign Up

Asymmetric Tri-training for Unsupervised Domain Adaptation

by   Kuniaki Saito, et al.

Deep-layered models trained on a large number of labeled samples boost the accuracy of many tasks. It is important to apply such models to different domains because collecting many labeled samples in various domains is expensive. In unsupervised domain adaptation, one needs to train a classifier that works well on a target domain when provided with labeled source samples and unlabeled target samples. Although many methods aim to match the distributions of source and target samples, simply matching the distribution cannot ensure accuracy on the target domain. To learn discriminative representations for the target domain, we assume that artificially labeling target samples can result in a good representation. Tri-training leverages three classifiers equally to give pseudo-labels to unlabeled samples, but the method does not assume labeling samples generated from a different domain.In this paper, we propose an asymmetric tri-training method for unsupervised domain adaptation, where we assign pseudo-labels to unlabeled samples and train neural networks as if they are true labels. In our work, we use three networks asymmetrically. By asymmetric, we mean that two networks are used to label unlabeled target samples and one network is trained by the samples to obtain target-discriminative representations. We evaluate our method on digit recognition and sentiment analysis datasets. Our proposed method achieves state-of-the-art performance on the benchmark digit recognition datasets of domain adaptation.


Deep Discriminative Learning for Unsupervised Domain Adaptation

The primary objective of domain adaptation methods is to transfer knowle...

General Domain Adaptation Through Proportional Progressive Pseudo Labeling

Domain adaptation helps transfer the knowledge gained from a labeled sou...

A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation

A domain adaptation method for urban scene segmentation is proposed in t...

Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation

To learn target discriminative representations, using pseudo-labels is a...

Loss-based Sequential Learning for Active Domain Adaptation

Active domain adaptation (ADA) studies have mainly addressed query selec...

Structured Discriminative Tensor Dictionary Learning for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) addresses the problem of performanc...

Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

Unsupervised domain adaptation aims to address the problem of classifyin...