Remote Sensing Image Scene Classification: Benchmark and State of the Art

Abstract

Remote sensing image scene classification plays an important role in a wide range of applications and hence has been receiving remarkable attention. During the past years, significant efforts have been made to develop various datasets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning datasets and methods for scene classification is still lacking. In addition, almost all existing datasets have a number of limitations, including the small scale of scene classes and the image numbers, the lack of image variations and diversity, and the saturation of accuracy. These limitations severely limit the development of new approaches especially deep learning-based methods. This paper first provides a comprehensive review of the recent progress. Then, we propose a large-scale dataset, termed "NWPU-RESISC45", which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This dataset contains 31,500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 (i) is large-scale on the scene classes and the total image number, (ii) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion, and (iii) has high within-class diversity and between-class similarity. The creation of this dataset will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed dataset and the results are reported as a useful baseline for future research.

This manuscript is the accepted version for Proceedings of the IEEE

References in corpus (3)

• A Survey on Object Detection in Optical Remote Sensing Images
• PCANet: A Simple Deep Learning Baseline for Image Classification?
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification

Cited by in corpus (99)

• Deep learning in remote sensing: a review
• Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
• Exploring Models and Data for Remote Sensing Image Caption Generation
• A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community
• Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning
• PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
• BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding
• A Review on Deep Learning in UAV Remote Sensing
• Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
• Building Instance Classification Using Street View Images
• Self-attention for raw optical Satellite Time Series Classification
• Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images
• Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art
• An Empirical Study of Remote Sensing Pretraining
• EVA-02: A Visual Representation for Neon Genesis
• Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification
• Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval
• Multiple instance dense connected convolution neural network for aerial image scene classification
• Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification
• Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings
• Multi-Granularity Canonical Appearance Pooling for Remote Sensing Scene Classification
• Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning
• Relation Network for Multi-label Aerial Image Classification
• RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing
• Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification
• CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding
• Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works
• Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
• RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classification
• Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Network
• Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark
• Using Deep Learning to Examine the Association between the Built Environment and Neighborhood Adult Obesity Prevalence
• DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification
• Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory
• Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion
• Improving Human-AI Collaboration With Descriptions of AI Behavior
• AI Security for Geoscience and Remote Sensing: Challenges and Future Trends
• Counting from Sky: A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark Method
• Aggregated Deep Local Features for Remote Sensing Image Retrieval
• UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
• One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
• MGML: Multi-Granularity Multi-Level Feature Ensemble Network for Remote Sensing Scene Classification
• High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network
• All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification
• Universal Domain Adaptation for Remote Sensing Image Scene Classification
• There Are No Data Like More Data- Datasets for Deep Learning in Earth Observation
• Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images
• Self-supervised Audiovisual Representation Learning for Remote Sensing Data
• A Novel Multi-Attention Driven System For Multi-Label Remote Sensing Image Classification
• An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images
• Solid Waste Detection, Monitoring and Mapping in Remote Sensing Images: A Survey
• Treepedia 2.0: Applying Deep Learning for Large-scale Quantification of Urban Tree Cover
• Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets
• Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification
• Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
• Multi-modal gated recurrent units for image description
• Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey
• Embedded Self-Distillation in Compact Multi-Branch Ensemble Network for Remote Sensing Scene Classification
• AllSpark: A Multimodal Spatio-Temporal General Intelligence Model with Ten Modalities via Language as a Reference Framework
• DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval
• Deep Learning Techniques for Geospatial Data Analysis
• Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey
• Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives
• Remote Sensing Image Scene Classification with Deep Neural Networks in JPEG 2000 Compressed Domain
• Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classification
• Backdoor Attacks for Remote Sensing Data with Wavelet Transform
• Relict landslide detection using Deep-Learning architectures for image segmentation in rainforest areas: A new framework
• Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
• Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization
• FuCiTNet: Improving the generalization of deep learning networks by the fusion of learned class-inherent transformations
• MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
• Ground-to-Aerial Person Search: Benchmark Dataset and Approach
• RSTeller: Scaling Up Visual Language Modeling in Remote Sensing with Rich Linguistic Semantics from Openly Available Data and Large Language Models
• A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data
• A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery
• Unsupervised Deep Features for Remote Sensing Image Matching via Discriminator Network
• Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization
• OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Prompt Tuning with Soft Context Sharing for Vision-Language Models
• A Novel Multi-scale Attention Feature Extraction Block for Aerial Remote Sensing Image Classification
• Multilingual Vision-Language Pre-training for the Remote Sensing Domain
• A Progressive Image Restoration Network for High-order Degradation Imaging in Remote Sensing
• ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations
• DDIPNet and DDIPNet+: Discriminant Deep Image Prior Networks for Remote Sensing Image Classification
• 3MOS: Multi-sources, Multi-resolutions, and Multi-scenes dataset for Optical-SAR image matching
• MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning
• Cross-View Image Retrieval -- Ground to Aerial Image Retrieval through Deep Learning
• Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing Images
• R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models
• One-Shot Domain Incremental Learning
• Region based Ensemble Learning Network for Fine-grained Classification
• Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images
• ViGEO: an Assessment of Vision GNNs in Earth Observation
• Regularizing Subspace Redundancy of Low-Rank Adaptation
• Will It Zero-Shot?: Predicting Zero-Shot Classification Performance For Arbitrary Queries
• Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection
• R-MTLLMF: Resilient Multi-Task Large Language Model Fusion at the Wireless Edge
• Survey on Remote Sensing Scene Classification: From Traditional Methods to Large Generative AI Models