MTG-Net, a multi-task graph convolutional network, segments CNV regions and vessels in OCTA images with Dice scores of 87.21% and 88.12%, and CNVSeg is released as a public dataset.
Querying labeled for unlabeled: Cross-image semantic consistency guided semi-supervised semantic segmenta- tion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network
MTG-Net, a multi-task graph convolutional network, segments CNV regions and vessels in OCTA images with Dice scores of 87.21% and 88.12%, and CNVSeg is released as a public dataset.