MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
Preprint
Abstract
Aerial scene recognition is a fundamental research problem in interpreting high-resolution aerial imagery. Over the past few years, most studies focus on classifying an image into one scene category, while in real-world scenarios, it is more often that a single image contains multiple scenes. Therefore, in this paper, we investigate a more practical yet underexplored task -- multi-scene recognition in single images. To this end, we create a large-scale dataset, called MultiScene, composed of 100,000 unconstrained high-resolution aerial images. Considering that manually labeling such images is extremely arduous, we resort to low-cost annotations from crowdsourcing platforms, e.g., OpenStreetMap (OSM). However, OSM data might suffer from incompleteness and incorrectness, which introduce noise into image labels. To address this issue, we visually inspect 14,000 images and correct their scene labels, yielding a subset of cleanly-annotated images, named MultiScene-Clean. With it, we can develop and evaluate deep networks for multi-scene recognition using clean data. Moreover, we provide crowdsourced annotations of all images for the purpose of studying network learning with noisy labels. We conduct experiments with extensive baseline models on both MultiScene-Clean and MultiScene to offer benchmarks for multi-scene recognition in single images and learning from noisy labels for this task, respectively. To facilitate progress, we make our dataset and trained models available on https://github.com/Hua-YS/Multi-Scene-Recognition.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networksISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Local climate zone-based urban land cover classification from multi-seasonal Sentinel-2 images with a recurrent residual networkISPRS Journal of Photogrammetry and Remote Sensing, 2019
- Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classificationISPRS Journal of Photogrammetry and Remote Sensing, 2019
- Land cover mapping at very high resolution with rotation equivariant CNNs: Towards small yet accurate modelsISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learningISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Beyond RGB: Very high resolution urban remote sensing with multimodal deep networksISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Classification with an edge: Improving semantic image segmentation with boundary detectionISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Multi-temporal and multi-source remote sensing image classification by nonlinear relative normalizationISPRS Journal of Photogrammetry and Remote Sensing, 2016
- Automatic landslide detection from remote-sensing imagery using a scene classification method based on BoVW and pLSAInternational Journal of Remote Sensing, 2012
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004