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

Remote sensing change detection between bi-temporal images receives growingconcentration from researchers. However, comparing two bi-temporal images fordetecting changes is challenging, as they demonstrate different appearances. Inthis paper, we propose a dual attentive generative adversarial network forachieving very high-resolution remote sensing image change detection tasks,which regards the detection model as a generator and attains the optimalweights of the detection model without increasing the parameters of thedetection model through generative-adversarial strategy, boosting the spatialcontiguity of predictions. Moreover, We design a multi-level feature extractorfor effectively fusing multi-level features, which adopts the pre-trained modelto extract multi-level features from bi-temporal images and introducesaggregate connections to fuse them. To strengthen the identification ofmulti-scale objects, we propose a multi-scale adaptive fusion module toadaptively fuse multi-scale features through various receptive fields anddesign a context refinement module to explore contextual dependencies.Moreover, the DAGAN framework utilizes the 4-layer convolution network as adiscriminator to identify whether the synthetic image is fake or real.Extensive experiments represent that the DAGAN framework has better performancewith 85.01% mean IoU and 91.48% mean F1 score than advanced methods on theLEVIR dataset.

A Dual Attentive Generative Adversarial Network for Remote Sensing Image Change Detection