AI RESEARCH
Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation
arXiv CS.CV
•
ArXi:2603.02727v3 Announce Type: replace Medical image segmentation requires models that preserve fine anatomical boundaries while remaining efficient for clinical deployment. While transformers capture long-range dependencies, they suffer from quadratic attention cost and large data requirements, whereas CNNs are compute-friendly yet struggle with global reasoning. Linear attention offers $\mathcal{O}(N)$ scaling, but often exhibits