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

ROI extraction is an active but challenging task in remote sensing because ofthe complicated landform, the complex boundaries and the requirement ofannotations. Weakly supervised learning (WSL) aims at learning a mapping frominput image to pixel-wise prediction under image-wise labels, which candramatically decrease the labor cost. However, due to the imprecision oflabels, the accuracy and time consumption of WSL methods are relativelyunsatisfactory. In this paper, we propose a two-step ROI extraction based oncontractive learning. Firstly, we present to integrate multiscale Grad-CAM toobtain pseudo pixelwise annotations with well boundaries. Then, to reduce thecompact of misjudgments in pseudo annotations, we construct a contrastivelearning strategy to encourage the features inside ROI as close as possible andseparate background features from foreground features. Comprehensiveexperiments demonstrate the superiority of our proposal. Code is available athttps://github.com/HE-Lingfeng/ROI-Extraction

Weakly-supervised ROI extraction method based on contrastive learning for remote sensing images