Unifying Remote Sensing Image Retrieval and Classification with Robust Fine-tuning

TL;DR

This paper introduces SF300, a large-scale dataset and a novel adversarial fine-tuning method that unifies remote sensing image retrieval and classification, significantly improving performance across multiple datasets.

Contribution

It presents a new large-scale dataset and a robust fine-tuning approach that jointly enhances remote sensing image retrieval and classification tasks.

Findings

Achieves performance boost on nine datasets compared to ImageNet baseline.

Introduces a unified framework for retrieval and classification.

Provides a new benchmark dataset SF300 for remote sensing images.

Abstract

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.