Abstract: Supervised methods on 3D medical image segmentation need large amounts of annotated data, but annotating is time-consuming. Also, existing 3D segmentation methods capture more global ...
Abstract: In this work, we replace Mamba in UMamba with recent xLSTM, and surprisingly, it works well! Convolutional Neural Networks (CNNs) and Vision Transformers (ViT) have been pivotal in ...