English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Currently, under supervised learning, a model pretrained by a large-scalenature scene dataset and then fine-tuned on a few specific task labeling datais the paradigm that has dominated the knowledge transfer learning. It hasreached the status of consensus solution for task-aware model training inremote sensing domain (RSD). Unfortunately, due to different categories ofimaging data and stiff challenges of data annotation, there is not a largeenough and uniform remote sensing dataset to support large-scale pretraining inRSD. Moreover, pretraining models on large-scale nature scene datasets bysupervised learning and then directly fine-tuning on diverse downstream tasksseems to be a crude method, which is easily affected by inevitable labelingnoise, 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 learningstrategy called ConSecutive PreTraining (CSPT) is proposed based on the idea ofnot stopping pretraining in natural language processing (NLP), which cangradually bridge the domain gap and transfer knowledge from the nature scenedomain to the RSD. The proposed CSPT also can release the huge potential ofunlabeled data for task-aware model training. Finally, extensive experimentsare carried out on twelve datasets in RSD involving three types of downstreamtasks (e.g., scene classification, object detection and land coverclassification) and two types of imaging data (e.g., optical and SAR). Theresults show that by utilizing the proposed CSPT for task-aware model training,almost all downstream tasks in RSD can outperform the previous method ofsupervised pretraining-then-fine-tuning and even surpass the state-of-the-art(SOTA) performance without any expensive labeling consumption and careful modeldesign.

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