Reliable Contrastive Learning for Semi-supervised Change Detection in Remote Sensing Images

Jia-Xin Wang; Teng Li; Si-Bao Chen; Jin Tang; Bin Luo; Richard Charles Wilson

doi:10.1109/TGRS.2022.3228016

Reliable Contrastive Learning for Semi-supervised Change Detection in Remote Sensing Images

Jia-Xin Wang, Teng Li^*, Si-Bao Chen^*, Jin Tang, Bin Luo, Richard Charles Wilson

^*Corresponding author for this work

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

With the development of deep learning in remote sensing image change detection, the dependence of change detection models on labeled data has become an important problem. To make better use of the comparatively resource-saving unlabeled data, the change detection method based on semi-supervised learning is worth further study. This paper proposes a reliable contrastive learning method for semi-supervised remote sensing image change detection. First, according to the task characteristics of change detection, we design the contrastive loss based on the changed areas to enhance the model’s feature extraction ability for changed objects. Then, to improve the quality of pseudo labels in semi-supervised learning, we use the uncertainty of unlabeled data to select reliable pseudo labels for model training. Combining these methods, semi-supervised change detection models can make full use of unlabeled data. Extensive experiments on three widely used change detection datasets demonstrate the effectiveness of the proposed method. The results show that our semi-supervised approach has better performance than related methods. The code is available at https://github.com/VCISwang/RC-Change-Detection.

Original language	English
Article number	4416413
Number of pages	13
Journal	IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Volume	60
DOIs	https://doi.org/10.1109/TGRS.2022.3228016
Publication status	Published - 7 Dec 2022

Bibliographical note

This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

Access to Document

10.1109/TGRS.2022.3228016

TGRS-2022-04457
This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Accepted author manuscript, 963 KB

Cite this

@article{e1261f18f875498c861b6a329f55181a,

title = "Reliable Contrastive Learning for Semi-supervised Change Detection in Remote Sensing Images",

abstract = "With the development of deep learning in remote sensing image change detection, the dependence of change detection models on labeled data has become an important problem. To make better use of the comparatively resource-saving unlabeled data, the change detection method based on semi-supervised learning is worth further study. This paper proposes a reliable contrastive learning method for semi-supervised remote sensing image change detection. First, according to the task characteristics of change detection, we design the contrastive loss based on the changed areas to enhance the model{\textquoteright}s feature extraction ability for changed objects. Then, to improve the quality of pseudo labels in semi-supervised learning, we use the uncertainty of unlabeled data to select reliable pseudo labels for model training. Combining these methods, semi-supervised change detection models can make full use of unlabeled data. Extensive experiments on three widely used change detection datasets demonstrate the effectiveness of the proposed method. The results show that our semi-supervised approach has better performance than related methods. The code is available at https://github.com/VCISwang/RC-Change-Detection.",

author = "Jia-Xin Wang and Teng Li and Si-Bao Chen and Jin Tang and Bin Luo and Wilson, {Richard Charles}",

note = "This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details",

year = "2022",

month = dec,

day = "7",

doi = "10.1109/TGRS.2022.3228016",

language = "English",

volume = "60",

journal = "IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING",

issn = "0196-2892",

publisher = "IEEE",

}

TY - JOUR

T1 - Reliable Contrastive Learning for Semi-supervised Change Detection in Remote Sensing Images

AU - Wang, Jia-Xin

AU - Li, Teng

AU - Chen, Si-Bao

AU - Tang, Jin

AU - Luo, Bin

AU - Wilson, Richard Charles

N1 - This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2022/12/7

Y1 - 2022/12/7

N2 - With the development of deep learning in remote sensing image change detection, the dependence of change detection models on labeled data has become an important problem. To make better use of the comparatively resource-saving unlabeled data, the change detection method based on semi-supervised learning is worth further study. This paper proposes a reliable contrastive learning method for semi-supervised remote sensing image change detection. First, according to the task characteristics of change detection, we design the contrastive loss based on the changed areas to enhance the model’s feature extraction ability for changed objects. Then, to improve the quality of pseudo labels in semi-supervised learning, we use the uncertainty of unlabeled data to select reliable pseudo labels for model training. Combining these methods, semi-supervised change detection models can make full use of unlabeled data. Extensive experiments on three widely used change detection datasets demonstrate the effectiveness of the proposed method. The results show that our semi-supervised approach has better performance than related methods. The code is available at https://github.com/VCISwang/RC-Change-Detection.

AB - With the development of deep learning in remote sensing image change detection, the dependence of change detection models on labeled data has become an important problem. To make better use of the comparatively resource-saving unlabeled data, the change detection method based on semi-supervised learning is worth further study. This paper proposes a reliable contrastive learning method for semi-supervised remote sensing image change detection. First, according to the task characteristics of change detection, we design the contrastive loss based on the changed areas to enhance the model’s feature extraction ability for changed objects. Then, to improve the quality of pseudo labels in semi-supervised learning, we use the uncertainty of unlabeled data to select reliable pseudo labels for model training. Combining these methods, semi-supervised change detection models can make full use of unlabeled data. Extensive experiments on three widely used change detection datasets demonstrate the effectiveness of the proposed method. The results show that our semi-supervised approach has better performance than related methods. The code is available at https://github.com/VCISwang/RC-Change-Detection.

U2 - 10.1109/TGRS.2022.3228016

DO - 10.1109/TGRS.2022.3228016

M3 - Article

SN - 0196-2892

VL - 60

JO - IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

JF - IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

M1 - 4416413

ER -