Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020-05-03T00:00:00.000000Z)

TL;DR

This article provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers and discusses the main challenges of remote sensing images classification and survey.

Abstract

Remote sensing image scene classification, which aims at labeling remote sensing images with a set of semantic categories based on their contents, has broad applications in a range of fields. Propelled by the powerful feature learning capabilities of deep neural networks, remote sensing image scene classification driven by deep learning has drawn remarkable attention and achieved significant breakthroughs. However, to the best of our knowledge, a comprehensive review of recent achievements regarding deep learning for scene classification of remote sensing images is still lacking. Considering the rapid evolution of this field, this article provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers. To be specific, we discuss the main challenges of remote sensing image scene classification and survey: first, autoencoder-based remote sensing image scene classification methods; second, convolutional neural network-based remote sensing image scene classification methods; and third, generative adversarial network-based remote sensing image scene classification methods. In addition, we introduce the benchmarks used for remote sensing image scene classification and summarize the performance of more than two dozen of representative algorithms on three commonly used benchmark datasets. Finally, we discuss the promising opportunities for further research.

Authors

Gong Cheng

4 papers

Xingxing Xie

1 papers

Junwei Han

10 papers

TL;DR

Abstract

Authors

References172 items

Cross-Scale Feature Fusion for Object Detection in Optical Remote Sensing Images

Classifier-Constrained Deep Adversarial Domain Adaptation for Cross-Domain Semisupervised Classification in Remote Sensing Images

Skip-Connected Covariance Network for Remote Sensing Scene Classification

Multisource Compensation Network for Remote Sensing Cross-Domain Scene Classification

Attention GANs: Unsupervised Deep Feature Learning for Aerial Scene Classification

Remote Sensing Scene Classification by Gated Bidirectional Network

Remotely sensed big data: evolution in model development for information extraction [point of view]

A Multi-Level Semantic Scene Interpretation Strategy for Change Interpretation in Remote Sensing Imagery

Graph convolutional network for multi-label VHR remote sensing scene recognition

Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark

AttentionBased Deep Feature Fusion for the Scene Classification of HighResolution Remote Sensing Images

Relation Network for Multilabel Aerial Image Classification

A Lightweight and Discriminative Model for Remote Sensing Scene Classification With Multidilation Pooling Module

A Feature Aggregation Convolutional Neural Network for Remote Sensing Scene Classification

Deep learning in remote sensing applications: A meta-analysis and review

Robust Space–Frequency Joint Representation for Remote Sensing Image Scene Classification

Scene Classification Using Hierarchical Wasserstein CNN

Deep Network Ensembles for Aerial Scene Classification

Scene Classification by Coupling Convolutional Neural Networks With Wasserstein Distance

Scale-Free Convolutional Neural Network for Remote Sensing Scene Classification

Deep Learning for Hyperspectral Image Classification: An Overview

Res2Net: A New Multi-Scale Backbone Architecture

Selective Kernel Networks

Lifelong Learning for Scene Recognition in Remote Sensing Images

Remote Sensing Image Scene Classification Using Rearranged Local Features

Remote Sensing Image Scene Classification Using CNN-CapsNet

Domain Adaptation for Convolutional Neural Networks-Based Remote Sensing Scene Classification

Bigearthnet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding

Siamese Convolutional Neural Networks for Remote Sensing Scene Classification

Learning Compact and Discriminative Stacked Autoencoder for Hyperspectral Image Classification

A Deep Scene Representation for Aerial Scene Classification

Deep Learning for Multilabel Land Cover Scene Categorization Using Data Augmentation

Scene Classification With Recurrent Attention of VHR Remote Sensing Images

Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection

Deep networks under scene-level supervision for multi-class geospatial object detection from remote sensing images

GAN-NL: Unsupervised Representation Learning for Remote Sensing Image Classification

A novel active learning technique for multi-label remote sensing image scene classification

SiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline In Vitro

IORN: An Effective Remote Sensing Image Scene Classification Framework

Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification

Adaptive Deep Sparse Semantic Modeling Framework for High Spatial Resolution Image Scene Classification

Remote Sensing Scene Classification Using Multilayer Stacked Covariance Pooling

Remote Sensing Image Retrieval Using Convolutional Neural Network Features and Weighted Distance

Multi-scale and Discriminative Part Detectors Based Features for Multi-label Image Classification

Exploring Hierarchical Convolutional Features for Hyperspectral Image Classification

Remote sensing image scene classification based on generative adversarial networks

Training Small Networks for Scene Classification of Remote Sensing Images via Knowledge Distillation

A Deep-Local-Global Feature Fusion Framework for High Spatial Resolution Imagery Scene Classification

Rotation-Insensitive and Context-Augmented Object Detection in Remote Sensing Images

Scene Classification Based on a Deep Random-Scale Stretched Convolutional Neural Network

Landslide Inventory Mapping From Bitemporal High-Resolution Remote Sensing Images Using Change Detection and Multiscale Segmentation

Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines

Monitoring of Urban Impervious Surfaces Using Time Series of High-Resolution Remote Sensing Images in Rapidly Urbanized Areas: A Case Study of Shenzhen

Siamese-GAN: Learning Invariant Representations for Aerial Vehicle Image Categorization

Asymmetric Adaptation of Deep Features for Cross-Domain Classification in Remote Sensing Imagery

Hydra: An Ensemble of Convolutional Neural Networks for Geospatial Land Classification

Large-Scale Remote Sensing Image Retrieval by Deep Hashing Neural Networks

Multilabel Remote Sensing Image Retrieval Using a Semisupervised Graph-Theoretic Method

MobileNetV2: Inverted Residuals and Linear Bottlenecks

When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs

Learning to Compare: Relation Network for Few-Shot Learning

A semi-supervised generative framework with deep learning features for high-resolution remote sensing image scene classification

Deep learning in remote sensing: a review

Squeeze-and-Excitation Networks

EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification

Remote Sensing Image Scene Classification Using Bag of Convolutional Features

Zero-Shot Classification with Discriminative Semantic Representation Learning

Deep Layer Aggregation

Multi-level monitoring of subtle urban changes for the megacities of China using high-resolution multi-view satellite imagery

Integrating Multilayer Features of Convolutional Neural Networks for Remote Sensing Scene Classification

Scene Classification Based on Multiscale Convolutional Neural Network

Remote Sensing Scene Classification by Unsupervised Representation Learning

RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data

Deep Feature Fusion for VHR Remote Sensing Scene Classification

Domain Adaptation Network for Cross-Scene Classification

Zero-Shot Scene Classification for High Spatial Resolution Remote Sensing Images