AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification

2017/04/24 by Gui-Song Xia, Jingwen Hu, Fan Hu +5 · 48 citations
Computer Science · Engineering · Environmental Science · #Advanced Neural Network Applications #Remote Sensing in Agriculture #Remote-Sensing Image Classification

paper · doi:10.1109/tgrs.2017.2685945

openalex created_date 2016/09/16 · openalex publication_date 2017/04/24 · openalex updated_date 2026/07/31

Abstract

Aerial scene classification, which aims to automatically label an aerial image with a specific semantic category, is a fundamental problem for understanding high-resolution remote sensing imagery. In recent years, it has become an active task in the remote sensing area, and numerous algorithms have been proposed for this task, including many machine learning and data-driven approaches. However, the existing data sets for aerial scene classification, such as UC-Merced data set and WHU-RS19, contain relatively small sizes, and the results on them are already saturated. This largely limits the development of scene classification algorithms. This paper describes the Aerial Image data set (AID): a large-scale data set for aerial scene classification. The goal of AID is to advance the state of the arts in scene classification of remote sensing images. For creating AID, we collect and annotate more than 10000 aerial scene images. In addition, a comprehensive review of the existing aerial scene classification techniques as well as recent widely used deep learning methods is given. Finally, we provide a performance analysis of typical aerial scene classification and deep learning approaches on AID, which can be served as the baseline results on this benchmark.

Citations

• Textural Features for Image Classification
• ImageNet Large Scale Visual Recognition Challenge
• A Fast Learning Algorithm for Deep Belief Nets

Cited by

• RS-Prune: Training-Free Data Pruning at High Ratios for Efficient Remote Sensing Diffusion Foundation Models
• Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains
• QMC-Net: Data-Aware Quantum Representations for Remote Sensing Image Classification
• MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
• VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing
• SceneMixer: Exploring Convolutional Mixing Networks for Remote Sensing Scene Classification
• GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes
• SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts
• GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding
• Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
• HIMOSA: Efficient Remote Sensing Image Super-Resolution with Hierarchical Mixture of Sparse Attention
• UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
• Co-Training Vision Language Models for Remote Sensing Multi-task Learning
• Hierarchical Semi-Supervised Active Learning for Remote Sensing
• FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding
• Improve Contrastive Clustering Performance by Multiple Fusing-Augmenting ViT Blocks
• AFM-Net: Advanced Fusing Hierarchical CNN Visual Priors with Global Sequence Modeling for Remote Sensing Image Scene Classification
• Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence
• Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning
• Enabling Near-realtime Remote Sensing via Satellite-Ground Collaboration of Large Vision-Language Models
• Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges
• Deep Learning Based Domain Adaptation Methods in Remote Sensing: A Comprehensive Survey
• Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification
• Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models
• DescribeEarth: Describe Anything for Remote Sensing Images
• Environment-Aware Satellite Image Generation with Diffusion Models
• Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
• MVT: Mask-Grounded Vision-Language Models for Taxonomy-Aligned Land-Cover Tagging
• Topic-based label distribution learning to exploit label ambiguity for scene classification
• RS-OOD: A Vision-Language Augmented Framework for Out-of-Distribution Detection in Remote Sensing
• A Comprehensive Review of Agricultural Parcel and Boundary Delineation from Remote Sensing Images: Recent Progress and Future Perspectives
• Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges
• Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision
• SU-ESRGAN: Semantic and Uncertainty-Aware ESRGAN for Super-Resolution of Satellite and Drone Imagery with Fine-Tuning for Cross Domain Evaluation
• Object Recognition Datasets and Challenges: A Review
• Lightweight Remote Sensing Scene Classification on Edge Devices via Knowledge Distillation and Early-exit
• RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning
• Dual-Stream Global-Local Feature Collaborative Representation Network for Scene Classification of Mining Area
• Exploring Scalable Unified Modeling for General Low-Level Vision
• Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection
• SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing
• Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score
• GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing
• ConBatch-BAL: Batch Bayesian Active Learning under Budget Constraints
• CGEarthEye:A High-Resolution Remote Sensing Vision Foundation Model Based on the Jilin-1 Satellite Constellation
• On the Domain Robustness of Contrastive Vision-Language Models
• Remote Sensing Large Vision-Language Model: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modeling
• MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classification

Related

• AID++: An Updated Version of AID on Scene Classification
• Recent advances and opportunities in scene classification of aerial images with deep models
• Creating Ensembles of Classifiers through UMDA for Aerial Scene Classification
• On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AID
• A Multi-Stage Duplex Fusion ConvNet for Aerial Scene Classification