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/

Zendy Pro

Presents the zaia usage as premium feature

ZAIA

Presents AI Discovery search usage as a premium feature

AI Discovery

Presents AI Discovery explain and summary usage as a premium feature

Content Analysis

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Presents the pdf analysis as premium feature

PDF Analysis

1500 Top-up

3000 Top-up

Zendy Basic

2500 Top-up

Zendy Unlimited

Presents the access of premium content as premium feature

Premium Content

With the increasing application of deep learning in various domains, salientobject detection in optical remote sensing images (ORSI-SOD) has attractedsignificant attention. However, most existing ORSI-SOD methods predominantlyrely on local information from low-level features to infer salient boundarycues and supervise them using boundary ground truth, but fail to sufficientlyoptimize and protect the local information, and almost all approaches ignorethe potential advantages offered by the last layer of the decoder to maintainthe integrity of saliency maps. To address these issues, we propose a novelmethod named boundary-semantic collaborative guidance network (BSCGNet) withdual-stream feedback mechanism. First, we propose a boundary protectioncalibration (BPC) module, which effectively reduces the loss of edge positioninformation during forward propagation and suppresses noise in low-levelfeatures without relying on boundary ground truth. Second, based on the BPCmodule, a dual feature feedback complementary (DFFC) module is proposed, whichaggregates boundary-semantic dual features and provides effective feedback tocoordinate features across different layers, thereby enhancing cross-scaleknowledge communication. Finally, to obtain more complete saliency maps, weconsider the uniqueness of the last layer of the decoder for the first time andpropose the adaptive feedback refinement (AFR) module, which further refinesfeature representation and eliminates differences between features through aunique feedback mechanism. Extensive experiments on three benchmark datasetsdemonstrate that BSCGNet exhibits distinct advantages in challenging scenariosand outperforms the 17 state-of-the-art (SOTA) approaches proposed in recentyears. Codes and results have been released on GitHub:https://github.com/YUHsss/BSCGNet.

Boundary-semantic collaborative guidance network with dual-stream feedback mechanism for salient object detection in optical remote sensing imagery