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

Fully convolutional networks have shown outstanding performance in thesalient object detection (SOD) field. The state-of-the-art (SOTA) methods havea tendency to become deeper and more complex, which easily homogenize theirlearned deep features, resulting in a clear performance bottleneck. In sharpcontrast to the conventional ``deeper'' schemes, this paper proposes a``wider'' network architecture which consists of parallel sub networks withtotally different network architectures. In this way, those deep featuresobtained via these two sub networks will exhibit large diversity, which willhave large potential to be able to complement with each other. However, a largediversity may easily lead to the feature conflictions, thus we use the denseshort-connections to enable a recursively interaction between the parallel subnetworks, pursuing an optimal complementary status between multi-model deepfeatures. Finally, all these complementary multi-model deep features will beselectively fused to make high-performance salient object detections. Extensiveexperiments on several famous benchmarks clearly demonstrate the superiorperformance, good generalization, and powerful learning ability of the proposedwider framework.

Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks