Adding attention gates and a label-guided pixel contrastive loss to a KAN-based U-Net yields small but consistent F1 improvements across five retinal vessel datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Novel Extraction of Discriminative Fine-Grained Feature to Improve Retinal Vessel Segmentation
Adding attention gates and a label-guided pixel contrastive loss to a KAN-based U-Net yields small but consistent F1 improvements across five retinal vessel datasets.