Remote Sensing Image Scene Classification: Benchmark and State of the Art
By Gong Cheng, Junwei Han, Xiaoqiang Lu. 2017
2,849 citations recorded by the source corpus.
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 data sets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning data sets and methods for scene classification is still lacking. In addition, almost all existing data sets 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 data set, termed “NWPU-RESISC45,” which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This data set contains 31 500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 1) is large-scale on the scene classes and the total image number; 2) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion; and 3) has high within-class diversity and between-class similarity. The creation of this data set will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed data set, and the results are reported as a useful baseline for future research.
Subfields: Computer Vision and Pattern Recognition, Media Technology, Ocean Engineering, 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
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Ming-Hsuan Yang
- Xiaogang Wang
- Jitendra Malik
- Andrew Zisserman
- Andrea Vedaldi
In Media Technology
- Liangpei Zhang
- Gong Cheng
- Junwei Han
- Jocelyn Chanussot
- Antonio J. Plaza
- Shutao Li
- Xiaoqiang Lu
- Bo Du
In Ocean Engineering
- Gong Cheng
- Junwei Han
- Liangpei Zhang
- Vladimir Risojevic
- Xiaoqiang Lu
- Antonio J. Plaza
- Marco Körner
- Vladan Stojnić
In Evaluation & Benchmarks
- Neil Houlsby
- Xiaohua Zhai
- Vladimir Risojevic
- Vladan Stojnić
- Phillip Isola
- Guisong Xia
- Dacheng Tao
- Mario Lucic
Citations in the corpus
- Learning Transferable Visual Models From Natural Language Supervision (2021, background): “…Recognition 2013 dataset (Goodfellow et al., 2015), STL-10 (Coates et al., 2011), EuroSAT (Helber et al., 2019), the NWPURESISC45 dataset (Cheng et al., 2017), the German Traffic Sign Recognition Benchmark (GTSRB) dataset (Stallkamp et al., 2011), the KITTI dataset (Geiger et al., 2012),…”
- On Robustness and Transferability of Convolutional Neural Networks (2020, background): “The specialized group contains remote sensing datasets EuroSAT [25] and Resisc45 [8], and medical image datasets Patch Camelyon [67] and Diabetic Retinopathy [34].”
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019, background): “Resisc45 (Cheng et al., 2017) The Remote Sensing Image Scene Classification (RESISC) dataset is a scene classification task from remote sensing images.”
- EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification (2017, methodology): “In the context of deep learning, the deep CNNs used in this paper have been trained from scratch or fine-tuned by using a pretrained network [6], [7], [16], [19], [31].”
- CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, neutral): “, 2012), RESISC45 (Cheng et al., 2017), STL10 (Coates et al.”
- Visual Prompt Tuning (2022, neutral): “800/1000 200 10,000 Caltech101 [43] 102 6,084 DTD [11] 47 1,880 Flowers102 [55] 102 6,149 Pets [57] 37 3,669 SVHN [54] 10 26,032 Sun397 [76] 397 21,750 Patch Camelyon [69] Specialized 2 800/1000 200 32,768 EuroSAT [29] 10 5,400 Resisc45 [10] 45 6,300 Retinopathy [36] 5 42,670 Clevr/count [34]”
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers (2021, methodology): “For Resisc45, we use only 60% of the training split for training, and another 20% for validation, and 20% for computing test metrics.”
- First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning (2023, background): “[6] Gong Cheng, Junwei Han, and Xiaoqiang Lu.”
- Reproducible Scaling Laws for Contrastive Language-Image Learning (2022, background): “In addition, we fine-tune and evaluate on eight diverse datasets where zero-shot models perform poorly [55, 31]: Cars [41], DTD [14], EuroSAT [21], GTSRB [68], MNIST [44], RESISC45 [13], SUN397 [78], and SVHN [50].”
- Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning (2022, methodology): “For these experiments, we use a lightweight pretraining setting, where we pretrain for 300 epochs on FMoW (rather than 800) and use a ViT-Base encoder (rather than ViT-Large), and evaluate using a kNN evaluation on RESISC-45 at 100% and 50% of its native GSD.”
- Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community (2017, methodology): “Cheng et al.1 discuss traditional hand-crafted features such as the histogram of ordered gradients (HOG), which is a feature of the scale-invariant feature transform (SIFT), color histograms, local binary patterns (LBP), etc.”
- Exploring Visual Prompts for Adapting Large-Scale Models (2022, methodology): “To evaluate how well visual prompts adapt a model to new tasks, we measure performance across 12 datasets: CIFAR100, CIFAR10 [25], Flowers102 [34], Food101 [3], EuroSAT [17], SUN397 [45], DTD [9], UCF101 [43], SVHN [33], OxfordPets [35], Resisc45 [7], and CLEVR [21].”
- An Empirical Study of Remote Sensing Pretraining (2022, methodology): “The existing literatures [21] reveal that the finetuning strategy performs better than the other ones.”
- Object-Oriented LULC Classification in Google Earth Engine Combining SNIC, GLCM, and Machine Learning Algorithms (2020, background): “These layers provide more effective feature representations through multiple abstraction levels which result very effective in discovering complex structures and discriminative information hidden in multi-dimensional data [25].”