TransNorm: Transformer Provides a Strong Spatial Normalization Mechanism for a Deep Segmentation Model

by   Reza Azad, et al.

In the past few years, convolutional neural networks (CNNs), particularly U-Net, have been the prevailing technique in the medical image processing era. Specifically, the seminal U-Net, as well as its alternatives, have successfully managed to address a wide variety of medical image segmentation tasks. However, these architectures are intrinsically imperfect as they fail to exhibit long-range interactions and spatial dependencies leading to a severe performance drop in the segmentation of medical images with variable shapes and structures. Transformers, preliminary proposed for sequence-to-sequence prediction, have arisen as surrogate architectures to precisely model global information assisted by the self-attention mechanism. Despite being feasibly designed, utilizing a pure Transformer for image segmentation purposes can result in limited localization capacity stemming from inadequate low-level features. Thus, a line of research strives to design robust variants of Transformer-based U-Net. In this paper, we propose Trans-Norm, a novel deep segmentation framework which concomitantly consolidates a Transformer module into both encoder and skip-connections of the standard U-Net. We argue that the expedient design of skip-connections can be crucial for accurate segmentation as it can assist in feature fusion between the expanding and contracting paths. In this respect, we derive a Spatial Normalization mechanism from the Transformer module to adaptively recalibrate the skip connection path. Extensive experiments across three typical tasks for medical image segmentation demonstrate the effectiveness of TransNorm. The codes and trained models are publicly available at


page 1

page 2

page 3

page 4

page 5

page 6

page 10

page 11


HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation

Convolutional neural networks (CNNs) have been the consensus for medical...

LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation

Medical image segmentation plays an essential role in developing compute...

Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation

Melanoma is caused by the abnormal growth of melanocytes in human skin. ...

Improving FHB Screening in Wheat Breeding Using an Efficient Transformer Model

Fusarium head blight is a devastating disease that causes significant ec...

TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation

U-Net based convolutional neural networks with deep feature representati...

Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets

Permutation invariant neural networks are a promising tool for making pr...

NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation

Convolutional neural networks (CNN) and Transformer variants have emerge...

Please sign up or login with your details

Forgot password? Click here to reset