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

By Gui-Song Xia, Jingwen Hu, Fan Hu, Baoguang Shi, Xiang Bai, Yanfei Zhong, Liangpei Zhang, Xiaoqiang Lu. 2016

2,251 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Ecology, Media Technology, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Ecology

In Media Technology

In Evaluation & Benchmarks

Citations in the corpus

EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification (2017, methodology): “The presented work extensively evaluated all proposed machine learning methods and concluded that deep CNNs outperformed non-deep learning approaches on the considered datasets [6], [15], [17], [27].”
Remote Sensing Image Scene Classification With Self-Supervised Paradigm Under Limited Labeled Samples (2020, background): “Aerial Image dataset (AID) [17] contains 10,000 samples of 30 classes, collected form Google Earth.”
Satlas: A Large-Scale, Multi-Task Dataset for Remote Sensing Image Understanding (2022, methodology): “Four are existing large-scale remote sensing datasets that involve classiﬁcation with between 21 and 63 categories: UCM [53], AID [52], RESISC45 [18], and FMoW [21].”
An Empirical Study of Remote Sensing Pretraining (2022, methodology): “[63], the Aerial Image Dataset (AID) [64] and the benchmark for REmote Sensing Image Scene Classification that is created by Northwestern Polytechnical University (NWPU-RESISC) [21], are used to comprehensively evaluate the impact of RSP and the representation ability of the above adopted backbones.”
Exploring Models and Data for Remote Sensing Image Caption Generation (2017, methodology): “In this data set, more than 10 000 remote sensing images are collected from Google Earth [3], Baidu Map, MapABC, and Tianditu.”
TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution (2024, neutral): “In this paper, we report the results of the super-resolution models on four remote sensing datasets, including AID [63], DOTA v1.”
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, methodology): “images [49], [74], [79], [80], [85], [124]–[131] to facilitate this field forward.”
Vision Transformers for Remote Sensing Image Classification (2021, methodology): “In our experiments, three well-known remote-sensing datasets are used for evaluation: Merced land-use dataset [57], Aerial image dataset (AID) [58], and the Optimal-31 [41] dataset.”
EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain (2024, methodology): “The NWPU-RESISC45 dataset is a large-scale publicly available dataset for RS image scene classification, published by North-western Polytechnical University.”
RSMamba: Remote Sensing Image Classification With State Space Model (2024, background): “Nonetheless, the complexity and diversity of remote sensing scenarios, coupled with the variable spatio-temporal resolution, present substantial challenges to automated remote sensing image classification [2], [3], [4], [5].”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “[33], [34], [35] and have promoted cutting-edge research in a”
DOTA: A Large-Scale Dataset for Object Detection in Aerial Images (2017, background): “Datasets have played an important role in data-driven research in recent years [36, 6, 14, 40, 38, 33].”
Hyperspectral Image Denoising Employing a Spatial–Spectral Deep Residual Convolutional Neural Network (2018, methodology): “DL has also been introduced into the geoscience and remote sensing community for data interpretation, analysis, and application [28]–[29], including aerial scene classification [30], synthetic aperture radar (SAR) image interpretation [31], pansharpening [32], and so on.”