Logistic regression projection-based feature representation for visual domain adaptation

The performance of visual image recognizers is considerably degraded while the training and test image sets not to follow the same distribution. In this study, we propose a novel method for unsupervised domain adaptation, called logistic regression projection-based feature representation. The propos...

Full description

Saved in:
Bibliographic Details
Published in:Signal, image and video processing image and video processing, 2020-09, Vol.14 (6), p.1115-1123
Main Authors: Hosseinzadeh, Hamidreza, Einalou, Zahra
Format: Article
Language:English
Subjects:
Adaptation
Computer Imaging
Computer Science
Domains
Error reduction
Forecasting
Image Processing and Computer Vision
Multimedia Information Systems
Original Paper
Pattern Recognition and Graphics
Representations
Signal,Image and Speech Processing
Training
Vision
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The performance of visual image recognizers is considerably degraded while the training and test image sets not to follow the same distribution. In this study, we propose a novel method for unsupervised domain adaptation, called logistic regression projection-based feature representation. The proposed method performs the semi-supervised learning method on both the source and the target domains to predict the pseudo-label values for unlabeled target data. We incorporate the predicted target data with the source training dataset in order to learn feature representation which can be compensated for the distribution mismatch between source and target data. The results of the experiments on adaptation to different visual domains demonstrated that this method can achieve superior classification accuracy compared to the state-of-the-art methods. Based on the quantitative evaluation, the proposed unsupervised domain adaptation method can reduce the error rates by 15.85% compared to a corresponding 1-nearest neighbor classifier.
ISSN:1863-1703
1863-1711
DOI:10.1007/s11760-020-01649-9