Deep Generative Matching Network for Optical and SAR Image Registration

Quan, Dou; Wang, Shuang; Liang, Xuefeng; Wang, Ruojing; Fang, Shuai; Hou, Biao; Jiao, Licheng

doi:10.1109/igarss.2018.8518653

Cited by 33 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MS-CA: Despite that excellent identification performance has been achieved, aforementioned methods focused on inputs produced by the same sensor, hence their effects may not be satisfactory on multi-sources correspondence identification with extremely small size of labeled dataset. Generative networks [1,22], which work as data augmentation processors, have been designed for overcoming data scarcity of MS-CA task. However, these methods focused on data augmentation, and only realized conclusive results as to whether generated data improved classification performance based on existing matching algorithm; hence, these generative networks cannot be regarded as integrated solutions.…”

Section: Related Methodsmentioning

confidence: 99%

“…With the rapid development of observation technologies, collaborative utilization of information from varied sensors has attracted considerable attention recently [1,2]. Many tasks benefit from multi-source information collaboration, where collaborative observation and monitoring applications with operational requirements have been extensively studied [3][4][5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning for Optical and SAR Data Correspondence Identification With Limited Training Labels

Zhang

Tao

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Section: Related Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Transfer Learning for Optical and SAR Data Correspondence Identification With Limited Training Labels

Zhang

Tao

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…In [150], Quan et al consider the use of GANs for generating examples for registration of optical and SAR imaging data. Since both optical and SAR observations of a scene may not even be available, traditional data augmentation techniques for deep learning-based models -employing geometric transformations for generating abundant training data- are out of the question for the problem at hand.…”

Section: Fusionmentioning

confidence: 99%

Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

Tsagkatakis

Aidini

Fotiadou

et al. 2019

Sensors

111

View full text Add to dashboard Cite

Deep Learning, and Deep Neural Networks in particular, have established themselves as the new norm in signal and data processing, achieving state-of-the-art performance in image, audio, and natural language understanding. In remote sensing, a large body of research has been devoted to the application of deep learning for typical supervised learning tasks such as classification. Less yet equally important effort has also been allocated to addressing the challenges associated with the enhancement of low-quality observations from remote sensing platforms. Addressing such channels is of paramount importance, both in itself, since high-altitude imaging, environmental conditions, and imaging systems trade-offs lead to low-quality observation, as well as to facilitate subsequent analysis, such as classification and detection. In this paper, we provide a comprehensive review of deep-learning methods for the enhancement of remote sensing observations, focusing on critical tasks including single and multi-band super-resolution, denoising, restoration, pan-sharpening, and fusion, among others. In addition to the detailed analysis and comparison of recently presented approaches, different research avenues which could be explored in the future are also discussed.

show abstract

“…In order to improve the quality and diversity of the training, a generative matching network (GMN) is proposed. It applies generative adversarial networks (GANs) to generate coupled training data [32]. In [40], a deep metric based on a fully convolutional neural network (FCN) is proposed to predict whether SAR-optical image pairs are aligned or not.…”

Section: Related Workmentioning

confidence: 99%