Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated dataset-specific methods. Moreover, typical tasks such as classification and retrieval lack a systematic evaluation on standard benchmarks and training datasets, which make it hard to identify durable and generalizable scientific contributions. We aim at unifying remote sensing image retrieval and classification with a new large-scale training and testing dataset, SF300, including both vertical and oblique aerial images and made available to the research community, and an associated fine-tuning method. We additionally propose a new adversarial fine-tuning method for global descriptors. We show that our framework systematically achieves a boost of retrieval and classification performance on nine different datasets compared to an ImageNet pretrained baseline, with currently no other method to compare to.
@article{arxiv.2102.13392,
title = {Unifying Remote Sensing Image Retrieval and Classification with Robust Fine-tuning},
author = {Dimitri Gominski and Valérie Gouet-Brunet and Liming Chen},
journal= {arXiv preprint arXiv:2102.13392},
year = {2023}
}
Comments
Performance margin with the proposed method is not statistically significant. Please refer to http://alegoria.ign.fr/en/SF300_dataset if you are interested in the dataset