MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation

by   Jiacheng Ruan, et al.

Recently, some pioneering works have preferred applying more complex modules to improve segmentation performances. However, it is not friendly for actual clinical environments due to limited computing resources. To address this challenge, we propose a light-weight model to achieve competitive performances for skin lesion segmentation at the lowest cost of parameters and computational complexity so far. Briefly, we propose four modules: (1) DGA consists of dilated convolution and gated attention mechanisms to extract global and local feature information; (2) IEA, which is based on external attention to characterize the overall datasets and enhance the connection between samples; (3) CAB is composed of 1D convolution and fully connected layers to perform a global and local fusion of multi-stage features to generate attention maps at channel axis; (4) SAB, which operates on multi-stage features by a shared 2D convolution to generate attention maps at spatial axis. We combine four modules with our U-shape architecture and obtain a light-weight medical image segmentation model dubbed as MALUNet. Compared with UNet, our model improves the mIoU and DSC metrics by 2.39 reduction in the number of parameters and computational complexity. In addition, we conduct comparison experiments on two skin lesion segmentation datasets (ISIC2017 and ISIC2018). Experimental results show that our model achieves state-of-the-art in balancing the number of parameters, computational complexity and segmentation performances. Code is available at


page 1

page 2

page 6


UNeXt: MLP-based Rapid Medical Image Segmentation Network

UNet and its latest extensions like TransUNet have been the leading medi...

MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation

Recently, Visual Transformer (ViT) has been widely used in various field...

MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation

Segmentation is essential for medical image analysis to identify and loc...

SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks

Recently, U-shaped networks have dominated the field of medical image se...

EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation

Transformer and its variants have been widely used for medical image seg...

UNet-2022: Exploring Dynamics in Non-isomorphic Architecture

Recent medical image segmentation models are mostly hybrid, which integr...

TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing

As convolution has empowered many smart applications, dynamic convolutio...

Please sign up or login with your details

Forgot password? Click here to reset