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

In this paper, we introduce Divide-and-Conquer into the salient objectdetection (SOD) task to enable the model to learn prior knowledge that is forpredicting the saliency map. We design a novel network, Divide-and-ConquerNetwork (DC-Net) which uses two encoders to solve different subtasks that areconducive to predicting the final saliency map, here is to predict the edgemaps with width 4 and location maps of salient objects and then aggregate thefeature maps with different semantic information into the decoder to predictthe final saliency map. The decoder of DC-Net consists of our newly designedtwo-level Residual nested-ASPP (ResASPP$^{2}$) modules, which have the abilityto capture a large number of different scale features with a small number ofconvolution operations and have the advantages of maintaining high resolutionall the time and being able to obtain a large and compact effective receptivefield (ERF). Based on the advantage of Divide-and-Conquer's parallel computing,we use Parallel Acceleration to speed up DC-Net, allowing it to achievecompetitive performance on six LR-SOD and five HR-SOD datasets under highefficiency (60 FPS and 55 FPS). Codes and results are available:https://github.com/PiggyJerry/DC-Net.

DC-Net: Divide-and-Conquer for Salient Object Detection