Details
| Original language | English |
|---|---|
| Pages (from-to) | 339-346 |
| Number of pages | 8 |
| Journal | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Volume | 3 |
| Issue number | 3 |
| Publication status | Published - 6 Jun 2016 |
| Event | 23rd International Society for Photogrammetry and Remote Sensing Congress, ISPRS 2016 - Prague, Czech Republic Duration: 12 Jul 2016 → 19 Jul 2016 |
Abstract
Domain adaptation techniques in transfer learning try to reduce the amount of training data required for classification by adapting a classifier trained on samples from a source domain to a new data set (target domain) where the features may have different distributions. In this paper, we propose a new technique for domain adaptation based on logistic regression. Starting with a classifier trained on training data from the source domain, we iteratively include target domain samples for which class labels have been obtained from the current state of the classifier, while at the same time removing source domain samples. In each iteration the classifier is re-trained, so that the decision boundaries are slowly transferred to the distribution of the target features. To make the transfer procedure more robust we introduce weights as a function of distance from the decision boundary and a new way of regularisation. Our methodology is evaluated using a benchmark data set consisting of aerial images and digital surface models. The experimental results show that in the majority of cases our domain adaptation approach can lead to an improvement of the classification accuracy without additional training data, but also indicate remaining problems if the difference in the feature distributions becomes too large.
Keywords
- Domain Adaptation, Knowledge Transfer, Logistic Regression, Machine Learning, Remote Sensing, Transfer Learning
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
- Environmental Science(all)
- Environmental Science (miscellaneous)
- Physics and Astronomy(all)
- Instrumentation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 3, No. 3, 06.06.2016, p. 339-346.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - ITERATIVE RE-WEIGHTED INSTANCE TRANSFER FOR DOMAIN ADAPTATION
AU - Paul, A.
AU - Rottensteiner, F.
AU - Heipke, C.
N1 - Copyright: Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2016/6/6
Y1 - 2016/6/6
N2 - Domain adaptation techniques in transfer learning try to reduce the amount of training data required for classification by adapting a classifier trained on samples from a source domain to a new data set (target domain) where the features may have different distributions. In this paper, we propose a new technique for domain adaptation based on logistic regression. Starting with a classifier trained on training data from the source domain, we iteratively include target domain samples for which class labels have been obtained from the current state of the classifier, while at the same time removing source domain samples. In each iteration the classifier is re-trained, so that the decision boundaries are slowly transferred to the distribution of the target features. To make the transfer procedure more robust we introduce weights as a function of distance from the decision boundary and a new way of regularisation. Our methodology is evaluated using a benchmark data set consisting of aerial images and digital surface models. The experimental results show that in the majority of cases our domain adaptation approach can lead to an improvement of the classification accuracy without additional training data, but also indicate remaining problems if the difference in the feature distributions becomes too large.
AB - Domain adaptation techniques in transfer learning try to reduce the amount of training data required for classification by adapting a classifier trained on samples from a source domain to a new data set (target domain) where the features may have different distributions. In this paper, we propose a new technique for domain adaptation based on logistic regression. Starting with a classifier trained on training data from the source domain, we iteratively include target domain samples for which class labels have been obtained from the current state of the classifier, while at the same time removing source domain samples. In each iteration the classifier is re-trained, so that the decision boundaries are slowly transferred to the distribution of the target features. To make the transfer procedure more robust we introduce weights as a function of distance from the decision boundary and a new way of regularisation. Our methodology is evaluated using a benchmark data set consisting of aerial images and digital surface models. The experimental results show that in the majority of cases our domain adaptation approach can lead to an improvement of the classification accuracy without additional training data, but also indicate remaining problems if the difference in the feature distributions becomes too large.
KW - Domain Adaptation
KW - Knowledge Transfer
KW - Logistic Regression
KW - Machine Learning
KW - Remote Sensing
KW - Transfer Learning
UR - http://www.scopus.com/inward/record.url?scp=85044544116&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-III-3-339-2016
DO - 10.5194/isprs-annals-III-3-339-2016
M3 - Conference article
AN - SCOPUS:85044544116
VL - 3
SP - 339
EP - 346
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
SN - 2194-9042
IS - 3
T2 - 23rd International Society for Photogrammetry and Remote Sensing Congress, ISPRS 2016
Y2 - 12 July 2016 through 19 July 2016
ER -