LANet: Lightweight Attention Network for Medical Image Segmentation

Status

03.11.2024

Accept

 The article is accepted and will be published soon…

03.11.2024
30.12.2023

Submit

The article is submitted in Springer proceedings of the ITTA-2024 conference (https://itta.cyber.az).

30.12.2023

Article

01.

Overview

LANet, a Lightweight Attention Network, are presented in the paper and incorporates an Efficient Fusion Attention (EFA) block and an Adaptive Feature Fusion (AFF) decoding block. The model adopts MobileViT as a lightweight backbone network with a small number of parameters, facilitating easy training and faster predictive inference.

02.

Efficient Fusion Attention

The EFA block enhances the model’s feature extraction capability by capturing task-relevant information while reducing redundancy in channel and spatial locations.

03.

Adaptive Feature Fusion

The AFF decoding block fuses the purified low-level features from the encoder with the sampled features from the decoder, enhancing the network’s understanding and expression of input features.

For more details (including source code), you can check it in – https://github.com/tyjcbzd/LANet

滚动至顶部