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

Contour-based instance segmentation methods have developed rapidly recentlybut feature rough and hand-crafted front-end contour initialization, whichrestricts the model performance, and an empirical and fixed backendpredicted-label vertex pairing, which contributes to the learning difficulty.In this paper, we introduce a novel contour-based method, named E2EC, forhigh-quality instance segmentation. Firstly, E2EC applies a novel learnablecontour initialization architecture instead of hand-crafted contourinitialization. This consists of a contour initialization module forconstructing more explicit learning goals and a global contour deformationmodule for taking advantage of all of the vertices' features better. Secondly,we propose a novel label sampling scheme, named multi-direction alignment, toreduce the learning difficulty. Thirdly, to improve the quality of the boundarydetails, we dynamically match the most appropriate predicted-ground truthvertex pairs and propose the corresponding loss function named dynamic matchingloss. The experiments showed that E2EC can achieve a state-of-the-artperformance on the KITTI INStance (KINS) dataset, the Semantic BoundariesDataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient foruse in real-time applications, with an inference speed of 36 fps for 512*512images on an NVIDIA A6000 GPU. Code will be released athttps://github.com/zhang-tao-whu/e2ec.

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation