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

Excellent performance has been achieved on instance segmentation but thequality on the boundary area remains unsatisfactory, which leads to a risingattention on boundary refinement. For practical use, an ideal post-processingrefinement scheme are required to be accurate, generic and efficient. However,most of existing approaches propose pixel-wise refinement, which eitherintroduce a massive computation cost or design specifically for differentbackbone models. Contour-based models are efficient and generic to beincorporated with any existing segmentation methods, but they often generateover-smoothed contour and tend to fail on corner areas. In this paper, wepropose an efficient contour-based boundary refinement approach, namedSharpContour, to tackle the segmentation of boundary area. We design a novelcontour evolution process together with an Instance-aware Point Classifier. Ourmethod deforms the contour iteratively by updating offsets in a discretemanner. Differing from existing contour evolution methods, SharpContourestimates each offset more independently so that it predicts much sharper andaccurate contours. Notably, our method is generic to seamlessly work withdiverse existing models with a small computational cost. Experiments show thatSharpContour achieves competitive gains whilst preserving high efficiency

SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation