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) are the backbone of state-of-artsemantic image segmentation systems. Recent work has shown that complementingCNNs with fully-connected conditional random fields (CRFs) can significantlyenhance their object localization accuracy, yet dense CRF inference iscomputationally expensive. We propose replacing the fully-connected CRF withdomain transform (DT), a modern edge-preserving filtering method in which theamount of smoothing is controlled by a reference edge map. Domain transformfiltering is several times faster than dense CRF inference and we show that ityields comparable semantic segmentation results, accurately capturing objectboundaries. Importantly, our formulation allows learning the reference edge mapfrom intermediate CNN features instead of using the image gradient magnitude asin standard DT filtering. This produces task-specific edges in an end-to-endtrainable system optimizing the target semantic segmentation quality.

Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform