Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain

TL;DR

This paper introduces ConSecutive PreTraining (CSPT), a self-supervised knowledge transfer strategy using vision transformers, which effectively bridges the domain gap in remote sensing and improves task performance without extensive labeling.

Contribution

The paper proposes CSPT, a novel self-supervised pretraining approach inspired by NLP, tailored for remote sensing, leveraging unlabeled data and vision transformers to enhance downstream task accuracy.

Findings

CSPT outperforms supervised pretraining-then-fine-tuning methods.

Almost all remote sensing tasks achieve state-of-the-art results with CSPT.

CSPT reduces reliance on labeled data and domain-specific large datasets.

Abstract

Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the status of consensus solution for task-aware model training in remote sensing domain (RSD). Unfortunately, due to different categories of imaging data and stiff challenges of data annotation, there is not a large enough and uniform remote sensing dataset to support large-scale pretraining in RSD. Moreover, pretraining models on large-scale nature scene datasets by supervised learning and then directly fine-tuning on diverse downstream tasks seems to be a crude method, which is easily affected by inevitable labeling noise, severe domain gaps and task-aware discrepancies. Thus, in this paper, considering the self-supervised pretraining and powerful vision transformer (ViT) architecture, a concise and effective knowledge transfer learning strategy called ConSecutive PreTraining (CSPT) is proposed based on the idea of not stopping pretraining in natural language processing (NLP), which can gradually bridge the domain gap and transfer knowledge from the nature scene domain to the RSD. The proposed CSPT also can release the huge potential of unlabeled data for task-aware model training. Finally, extensive experiments are carried out on twelve datasets in RSD involving three types of downstream tasks (e.g., scene classification, object detection and land cover classification) and two types of imaging data (e.g., optical and SAR). The results show that by utilizing the proposed CSPT for task-aware model training, almost all downstream tasks in RSD can outperform the previous method of supervised pretraining-then-fine-tuning and even surpass the state-of-the-art (SOTA) performance without any expensive labeling consumption and careful model design.