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 present a joint multi-task learning framework for semanticsegmentation and boundary detection. The critical component in the framework isthe iterative pyramid context module (PCM), which couples two tasks and storesthe shared latent semantics to interact between the two tasks. For semanticboundary detection, we propose the novel spatial gradient fusion to suppressnonsemantic edges. As semantic boundary detection is the dual task of semanticsegmentation, we introduce a loss function with boundary consistency constraintto improve the boundary pixel accuracy for semantic segmentation. Our extensiveexperiments demonstrate superior performance over state-of-the-art works, notonly in semantic segmentation but also in semantic boundary detection. Inparticular, a mean IoU score of 81:8% on Cityscapes test set is achievedwithout using coarse data or any external data for semantic segmentation. Forsemantic boundary detection, we improve over previous state-of-the-art works by9.9% in terms of AP and 6:8% in terms of MF(ODS).

Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts