KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

Understand

Most methods for medical image segmentation use U-Net or its variants as they have been successful in most of the applications.

• After a detailed analysis of these "traditional" encoder-decoder based approaches, we observed that they perform poorly in detecting smaller structures and are unable to segment boundary regions precisely.
• This issue can be attributed to the increase in receptive field size as we go deeper into the encoder.
• The extra focus on learning high level features causes the U-Net based approaches to learn less information about low-level features which are crucial for detecting small structures.