Loss-based Sequential Learning for Active Domain Adaptation

04/25/2022
by   Kyeongtak Han, et al.
0

Active domain adaptation (ADA) studies have mainly addressed query selection while following existing domain adaptation strategies. However, we argue that it is critical to consider not only query selection criteria but also domain adaptation strategies designed for ADA scenarios. This paper introduces sequential learning considering both domain type (source/target) or labelness (labeled/unlabeled). We first train our model only on labeled target samples obtained by loss-based query selection. When loss-based query selection is applied under domain shift, unuseful high-loss samples gradually increase, and the labeled-sample diversity becomes low. To solve these, we fully utilize pseudo labels of the unlabeled target domain by leveraging loss prediction. We further encourage pseudo labels to have low self-entropy and diverse class distributions. Our model significantly outperforms previous methods as well as baseline models in various benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/27/2017

Asymmetric Tri-training for Unsupervised Domain Adaptation

Deep-layered models trained on a large number of labeled samples boost t...
research
09/05/2022

Semi-Supervised Domain Adaptation by Similarity based Pseudo-label Injection

One of the primary challenges in Semi-supervised Domain Adaptation (SSDA...
research
03/12/2020

Fisher Deep Domain Adaptation

Deep domain adaptation models learn a neural network in an unlabeled tar...
research
10/03/2022

A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods

Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled targe...
research
07/14/2021

Zero-Round Active Learning

Active learning (AL) aims at reducing labeling effort by identifying the...
research
11/10/2017

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

A domain adaptation method for urban scene segmentation is proposed in t...
research
05/30/2020

Self-adaptive Re-weighted Adversarial Domain Adaptation

Existing adversarial domain adaptation methods mainly consider the margi...

Please sign up or login with your details

Forgot password? Click here to reset