Adding roughly 15 to 30 learnable Gabor and LoG filter parameters to a Swin-Unet patch embedding improves Dice scores by about one point on two medical segmentation benchmarks.
An integrated visualization system for surgical planning and guidance using image fusion and an open mr,
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
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
GLoG-CSUnet: Enhancing Vision Transformers with Adaptable Radiomic Features for Medical Image Segmentation
Adding roughly 15 to 30 learnable Gabor and LoG filter parameters to a Swin-Unet patch embedding improves Dice scores by about one point on two medical segmentation benchmarks.