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

Deep convolutional neural networks (CNNs) have delivered superior performancein many computer vision tasks. In this paper, we propose a novel deep fullyconvolutional network model for accurate salient object detection. The keycontribution of this work is to learn deep uncertain convolutional features(UCF), which encourage the robustness and accuracy of saliency detection. Weachieve this via introducing a reformulated dropout (R-dropout) after specificconvolutional layers to construct an uncertain ensemble of internal featureunits. In addition, we propose an effective hybrid upsampling method to reducethe checkerboard artifacts of deconvolution operators in our decoder network.The proposed methods can also be applied to other deep convolutional networks.Compared with existing saliency detection methods, the proposed UCF model isable to incorporate uncertainties for more accurate object boundary inference.Extensive experiments demonstrate that our proposed saliency model performsfavorably against state-of-the-art approaches. The uncertain feature learningmechanism as well as the upsampling method can significantly improveperformance on other pixel-wise vision tasks.

Learning Uncertain Convolutional Features for Accurate Saliency Detection