Research Progress on Few-Shot Learning for Remote Sensing Image Interpretation

Sun, Xian; Wang, Bing; Wang, Zhirui; Li, Hao; Li, Heng-Chao; Fu, Kun

doi:10.1109/jstars.2021.3052869

Cited by 157 publications

(88 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…• Top-down works, first build a large dataset with an important number of object-classes, mainly objects that can be recognised from remote sensing images, e.g., vehicles or soccer stadiums. Then, the studies analyse these images using a deep learning classification or detection models [6], [7], [10], [12], [19], [20], [29], [33], [28]. • Bottom-up works focus on solving a specific problem that involves one or few object classes, e.g., airports [3], [4], [21], [32], [35], trees [2], [13], [15], [27], clouds [17] and whales [16].…”

Section: Related Workmentioning

confidence: 99%

CI-Dataset and DetDSCI Methodology for Detecting Too Small and Too Large Critical Infrastructures in Satellite Images: Airports and Electrical Substations as Case Study

Pérez-Hernández¹,

Rodríguez-Ortega²,

Herrera³

et al. 2021

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

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

CI-Dataset and DetDSCI Methodology for Detecting Too Small and Too Large Critical Infrastructures in Satellite Images: Airports and Electrical Substations as Case Study

Pérez-Hernández¹,

Rodríguez-Ortega²,

Herrera³

et al. 2021

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

View full text Add to dashboard Cite

“…Following the success of deep learning and the increasing availability of remote sensing data, deep learning has been playing an increasingly important role in the field of remote sensing. With sufficient remote sensing data for training, researchers have focused on designing convolutional neural networks (CNNs) to perform feature selection [9], [10], [11], [12], extraction [13], [14], and coding [15] on high-resolution remote sensing images, thereby improving network performance. Meanwhile, remote sensing data also bring unprecedented challenges to deep learning.…”

Section: Introductionmentioning

confidence: 99%

Progressive Data Augmentation Method for Remote Sensing Ship Image Classification Based on Imaging Simulation System and Neural Style Transfer

Qu¹,

Liu²,

Li³

et al. 2021

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

View full text Add to dashboard Cite

Deep learning has shown great power in processing remote sensing data, especially for fine-grained remote sensing ship image classification. However, the lack of a large amount of effective training data greatly limits the performance of neural networks. Based on current data augmentation methods, images of ships on the sea generated for remote sensing have the problem of distortion, blurring, and poor diversity. To tackle this problem, we propose a novel progressive remote sensing ship image data augmentation method that combines ship simulation samples and a neural style transfer (NST) based network to generate a large amount of transferred remote sensing ship images. Our method consists of two stages. The first stage uses a visible light imaging simulation system (VLISS) to generate ship simulation samples through 3D models of real images. This stage can significantly increase the diversity of the training dataset. For the second stage, to eliminate the domain gap between real ship images and ship simulation samples, a few real images and a newly designed NSTbased network called Sim2RealNet are employed to realize style transfer from simulation samples to real images. The proposed method was applied to a variety of ship targets to verify its effectiveness compared to other data augmentation methods on remote sensing image classification tasks. The experimental results demonstrate the effectiveness of the proposed method.

show abstract

“…It can effectively extract the basic scattering mechanisms (surface scattering, double-bounce scattering and volume scattering) of different land covers. The information obtained can be used in applications such as classification and segmentation [8]. Currently, there are two different methods in CP decomposition, including the wave-dichotomy-theorem-based (WDT-based) methods [9] and model-based decomposition methods.…”

Section: Introductionmentioning

confidence: 99%

Polarimetric Decomposition With an Urban Area Descriptor for Compact Polarimetric SAR Data

Yin

Xiang

et al. 2021

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

View full text Add to dashboard Cite

The compact polarimetric (CP) synthetic aperture radar (SAR) can alleviate the drawbacks of the fully polarimetric (FP) SAR and provide more target information as compared to the conventional single polarimetric and dual polarimetric mode. However, the present decomposition methods for CP SAR have the problem of overestimation of volume scattering (OVS) among urban areas, especially the obliquely oriented buildings (OOBs). The OVS can cause considerable overestimation of volume scattering which leads to the misinterpretation of the scattering mechanism. In this paper, a new descriptor of OOBs for the CP SAR is introduced to reduce the volume scattering in the urban areas. And a new model-based decomposition method, which is applicable for both the π/4 mode and the CTLR mode, is proposed based on the descriptor. The Radarsat-2 FP SAR data is used to simulate the CP SAR data to validate our algorithm. The proposed method improves the double-bounce scattering component in different types of urban areas by about 10%.

show abstract

Research Progress on Few-Shot Learning for Remote Sensing Image Interpretation

Cited by 157 publications

References 82 publications

CI-Dataset and DetDSCI Methodology for Detecting Too Small and Too Large Critical Infrastructures in Satellite Images: Airports and Electrical Substations as Case Study

CI-Dataset and DetDSCI Methodology for Detecting Too Small and Too Large Critical Infrastructures in Satellite Images: Airports and Electrical Substations as Case Study

Progressive Data Augmentation Method for Remote Sensing Ship Image Classification Based on Imaging Simulation System and Neural Style Transfer

Polarimetric Decomposition With an Urban Area Descriptor for Compact Polarimetric SAR Data

Contact Info

Product

Resources

About