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 recent years, deep convolution neural networks (DCNNs) have achieved greatprospects in coronary artery vessel segmentation. However, it is difficult todeploy complicated models in clinical scenarios since high-performanceapproaches have excessive parameters and high computation costs. To tackle thisproblem, we propose \textbf{LightVessel}, a Similarity Knowledge DistillationFramework, for lightweight coronary artery vessel segmentation. Primarily, wepropose a Feature-wise Similarity Distillation (FSD) module for semantic-shiftmodeling. Specifically, we calculate the feature similarity between thesymmetric layers from the encoder and decoder. Then the similarity istransferred as knowledge from a cumbersome teacher network to a non-trainedlightweight student network. Meanwhile, for encouraging the student model tolearn more pixel-wise semantic information, we introduce the AdversarialSimilarity Distillation (ASD) module. Concretely, the ASD module aims toconstruct the spatial adversarial correlation between the annotation andprediction from the teacher and student models, respectively. Through the ASDmodule, the student model obtains fined-grained subtle edge segmented resultsof the coronary artery vessel. Extensive experiments conducted on ClinicalCoronary Artery Vessel Dataset demonstrate that LightVessel outperforms variousknowledge distillation counterparts.

LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation