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

Weakly-supervised learning (WSL) has been proposed to alleviate the conflictbetween data annotation cost and model performance through employingsparsely-grained (i.e., point-, box-, scribble-wise) supervision and has shownpromising performance, particularly in the image segmentation field. However,it is still a very challenging task due to the limited supervision, especiallywhen only a small number of labeled samples are available. Additionally, almostall existing WSL segmentation methods are designed for star-convex structureswhich are very different from curvilinear structures such as vessels andnerves. In this paper, we propose a novel sparsely annotated segmentationframework for curvilinear structures, named YoloCurvSeg. A very essentialcomponent of YoloCurvSeg is image synthesis. Specifically, a backgroundgenerator delivers image backgrounds that closely match the real distributionsthrough inpainting dilated skeletons. The extracted backgrounds are thencombined with randomly emulated curves generated by a Space ColonizationAlgorithm-based foreground generator and through a multilayer patch-wisecontrastive learning synthesizer. In this way, a synthetic dataset with bothimages and curve segmentation labels is obtained, at the cost of only one or afew noisy skeleton annotations. Finally, a segmenter is trained with thegenerated dataset and possibly an unlabeled dataset. The proposed YoloCurvSegis evaluated on four publicly available datasets (OCTA500, CORN, DRIVE andCHASEDB1) and the results show that YoloCurvSeg outperforms state-of-the-artWSL segmentation methods by large margins. With only one noisy skeletonannotation (respectively 0.14\%, 0.03\%, 1.40\%, and 0.65\% of the fullannotation), YoloCurvSeg achieves more than 97\% of the fully-supervisedperformance on each dataset. Code and datasets will be released athttps://github.com/llmir/YoloCurvSeg.

YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure Segmentation