PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
This addresses a critical bottleneck for researchers in remote sensing by providing a dedicated benchmark to develop and compare RSIR methods, particularly for deep learning approaches that require large datasets.
The authors tackled the problem of limited benchmark datasets for remote sensing image retrieval (RSIR) by introducing PatternNet, a new large-scale dataset with 38 classes and 800 images per class, and evaluated over 35 methods to establish baseline results.
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.