PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval

Abstract

Remote sensing image retrieval(RSIR), which aims to efficiently retrieve data of interest from large collections of remote sensing data, is a fundamental task in remote sensing. Over the past several decades, there has been significant effort to extract powerful feature representations for this task since the retrieval performance depends on the representative strength of the features. Benchmark datasets are also critical for developing, evaluating, and comparing RSIR approaches. Current benchmark datasets are deficient in that 1) they were originally collected for land use/land cover classification and not image retrieval, 2) they are relatively small in terms of the number of classes as well the number of sample images per class, and 3) the retrieval performance has saturated. These limitations have severely restricted the development of novel feature representations for RSIR, particularly the recent deep-learning based features which require large amounts of training data. We therefore present in this paper, a new large-scale remote sensing dataset termed "PatternNet" that was collected specifically for RSIR. PatternNet was collected from high-resolution imagery and contains 38 classes with 800 images per class. We also provide a thorough review of RSIR approaches ranging from traditional handcrafted feature based methods to recent deep learning based ones. We evaluate over 35 methods to establish extensive baseline results for future RSIR research using the PatternNet benchmark.

49 pages

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
• Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
• Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

Cited by in corpus (24)

• BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding
• Region Convolutional Features for Multi-Label Remote Sensing Image Retrieval
• Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study
• Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings
• Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Network
• Asymmetric Hash Code Learning for Remote Sensing Image Retrieval
• An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images
• Exploiting Deep Features for Remote Sensing Image Retrieval: A Systematic Investigation
• Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey
• DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval
• Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives
• BigEarthNet Dataset with A New Class-Nomenclature for Remote Sensing Image Understanding
• RSTeller: Scaling Up Visual Language Modeling in Remote Sensing with Rich Linguistic Semantics from Openly Available Data and Large Language Models
• Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization
• Virtual SAR: A Synthetic Dataset for Deep Learning based Speckle Noise Reduction Algorithms
• On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AID
• Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing Images
• Testing the Efficient Network TRaining (ENTR) Hypothesis: initially reducing training image size makes Convolutional Neural Network training for image recognition tasks more efficient
• Remote Sensing Image Classification with the SEN12MS Dataset
• Unifying Remote Sensing Image Retrieval and Classification with Robust Fine-tuning
• Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images
• Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weighting