MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation

arXiv:2305.08396v5 Announce Type: replace-cross
Abstract: Since their emergence, Convolutional Neural Networks (CNNs) have made significant strides in medical image analysis. However, the local nature of the convolution operator may pose a limitation for capturing global and long-range interactions in CNNs. Recently, Transformers have gained popularity in the computer vision community and also in medical image segmentation due to their ability to process global features effectively. The scalability issues of the self-attention mechanism and lack of the CNN-like inductive bias may …

abstract analysis arxiv attention cnns community computer computer vision convolution convolutional neural networks cs.cv cs.lg eess.iv emergence global however image interactions medical nature networks neural networks segmentation transformers type unet vision