3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in landmark-based-segmentation-1
No benchmarks available.
Use these libraries to find landmark-based-segmentation-1 models and implementations
No datasets available.
No subtasks available.
The experimental results suggest that HybridGNet produces accurate and anatomically plausible landmark-based segmentations, by naturally incorporating shape constraints within the decoding process via spectral convolutions.
It is shown how state-of-the-art pixel-level segmentation models fail in naively learning this task, and proposed is HybridGNet, a landmark-based segmentation model which learns the available anatomical structures using graph-based representations.
Adding a benchmark result helps the community track progress.