In-domain representation learning for remote sensing

15 Nov 2019  ·  Maxim Neumann, Andre Susano Pinto, Xiaohua Zhai, Neil Houlsby ·

Given the importance of remote sensing, surprisingly little attention has been paid to it by the representation learning community. To address it and to establish baselines and a common evaluation protocol in this domain, we provide simplified access to 5 diverse remote sensing datasets in a standardized form. Specifically, we investigate in-domain representation learning to develop generic remote sensing representations and explore which characteristics are important for a dataset to be a good source for remote sensing representation learning. The established baselines achieve state-of-the-art performance on these datasets.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Multi-Label Image Classification BigEarthNet ResNet50 mAP (macro) 75.36 # 1
Image Classification EuroSAT ResNet50 Accuracy (%) 99.2 # 3
Image Classification RESISC45 ResNet50 Top 1 Accuracy 96.83 # 1
Image Classification So2Sat LCZ42 ResNet50 Accuracy 63.25 # 1
Scene Classification UC Merced Land Use Dataset ResNet50 Accuracy (%) 99.61 # 4


No methods listed for this paper. Add relevant methods here