DO WE STILL NEED IMAGENET PRE-TRAINING IN REMOTE SENSING SCENE CLASSIFICATION?

Due to the scarcity of labeled data, using supervised models pre-trained on ImageNet is a de facto standard in remote sensing scene classification. Recently, the availability of larger high resolution remote sensing (HRRS) image datasets and progress in self-supervised learning have brought up the questions of whether supervised ImageNet pre-training is still necessary for remote sensing scene classification and would supervised pre-training on HRRS image datasets or self-supervised pre-training on ImageNet achieve better results on target remote sensing scene classification tasks. To answer these questions, in this paper we both train models from scratch and fine-tune supervised and self-supervised ImageNet models on several HRRS image datasets. We also evaluate the transferability of learned representations to HRRS scene classification tasks and show that self-supervised pre-training outperforms the supervised one, while the performance of HRRS pre-training is similar to self-supervised pre-training or slightly lower. Finally, we propose using an ImageNet pre-trained model combined with a second round of pre-training using in-domain HRRS images, i.e. domain-adaptive pre-training. The experimental results show that domain-adaptive pre-training results in models that achieve state-of-the-art results on HRRS scene classification benchmarks. The source code and pre-trained models are available at https://github.com/risojevicv/RSSC-transfer.

Automated summary

The study investigates the effectiveness of using supervised and self-supervised pre-training models in remote sensing scene classification, and proposes domain-adaptive pre-training combining both methods. Results show that self-supervised pre-training outperforms supervised pre-training, and domain-adaptive pre-training achieves state-of-the-art results in HRRS scene classification.