Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation network

Semantic segmentation is a critical task in computer vision. Constructing complex semantic segmentation models with high accuracy, low spatial occupancy, and low computational complexity remains a challenge. To address this, this paper proposes a semantic segmentation network based on a hybrid archi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yane Li, Zhichao Chen, Hongxia Qi, Ming Fan, Lihua Li
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Machine Learning: Science and Technology
Subjects:
Online Access:https://doi.org/10.1088/2632-2153/add853
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849328427778179072
author Yane Li
Zhichao Chen
Hongxia Qi
Ming Fan
Lihua Li
author_facet Yane Li
Zhichao Chen
Hongxia Qi
Ming Fan
Lihua Li
author_sort Yane Li
collection DOAJ
description Semantic segmentation is a critical task in computer vision. Constructing complex semantic segmentation models with high accuracy, low spatial occupancy, and low computational complexity remains a challenge. To address this, this paper proposes a semantic segmentation network based on a hybrid architecture of convolutional neural network and Transformer, named shuffle window transformer DeeplabV3+ (SWT-DeepLabV3+). The network introduces a new module, called the SWT. When the window size is fixed, by integrating window attention (WA) and shuffle WA mechanisms, cross-window global context modeling with linear computational complexity is achieved. Additionally, we enhance the atrous spatial pyramid pooling (ASPP) by incorporating strip pooling to construct a strip ASPP, effectively extracting both regular and irregular multi-scale (MS) features. Simultaneously, the network adopts adaptive spatial feature fusion in the shallow layers. Dynamic adjustment of MS feature weights improves the backbone network’s ability to capture shallow discriminative features. Experimental results demonstrate that on three public datasets (PASCAL VOC 2012, Cityscapes, and CamVid), SWT-DeepLabV3+ exhibits outstanding segmentation performance under conditions of lower parameter count and computational cost, validating the model’s capability to achieve efficient processing while maintaining high accuracy.
format Article
id doaj-art-7d24bcded2254dbdba8ae7259add2c3e
institution Kabale University
issn 2632-2153
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Machine Learning: Science and Technology
spelling doaj-art-7d24bcded2254dbdba8ae7259add2c3e2025-08-20T03:47:36ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016202503910.1088/2632-2153/add853Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation networkYane Li0https://orcid.org/0000-0003-0065-7750Zhichao Chen1Hongxia Qi2Ming Fan3https://orcid.org/0000-0002-5626-7076Lihua Li4https://orcid.org/0000-0003-0435-6453College of Mathematics and Computer Science, Zhejiang A&F University , Hangzhou 311300, People’s Republic of ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University , Hangzhou 311300, People’s Republic of ChinaDepartment of Echocardiography, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College , Beijing, People’s Republic of ChinaInstitute of Biomedical Engineering and Instrumentation, Hangzhou Dianzi University , Hangzhou 310018, People’s Republic of ChinaInstitute of Biomedical Engineering and Instrumentation, Hangzhou Dianzi University , Hangzhou 310018, People’s Republic of ChinaSemantic segmentation is a critical task in computer vision. Constructing complex semantic segmentation models with high accuracy, low spatial occupancy, and low computational complexity remains a challenge. To address this, this paper proposes a semantic segmentation network based on a hybrid architecture of convolutional neural network and Transformer, named shuffle window transformer DeeplabV3+ (SWT-DeepLabV3+). The network introduces a new module, called the SWT. When the window size is fixed, by integrating window attention (WA) and shuffle WA mechanisms, cross-window global context modeling with linear computational complexity is achieved. Additionally, we enhance the atrous spatial pyramid pooling (ASPP) by incorporating strip pooling to construct a strip ASPP, effectively extracting both regular and irregular multi-scale (MS) features. Simultaneously, the network adopts adaptive spatial feature fusion in the shallow layers. Dynamic adjustment of MS feature weights improves the backbone network’s ability to capture shallow discriminative features. Experimental results demonstrate that on three public datasets (PASCAL VOC 2012, Cityscapes, and CamVid), SWT-DeepLabV3+ exhibits outstanding segmentation performance under conditions of lower parameter count and computational cost, validating the model’s capability to achieve efficient processing while maintaining high accuracy.https://doi.org/10.1088/2632-2153/add853semantic segmentationshuffle window transformerconvolutional neural networkDeepLabV3+
spellingShingle Yane Li
Zhichao Chen
Hongxia Qi
Ming Fan
Lihua Li
Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation network
Machine Learning: Science and Technology
semantic segmentation
shuffle window transformer
convolutional neural network
DeepLabV3+
title Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation network
title_full Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation network
title_fullStr Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation network
title_full_unstemmed Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation network
title_short Shuffle window transformer DeepLabV3+: a lightweight convolutional neural network and transformer based hybrid semantic segmentation network
title_sort shuffle window transformer deeplabv3 a lightweight convolutional neural network and transformer based hybrid semantic segmentation network
topic semantic segmentation
shuffle window transformer
convolutional neural network
DeepLabV3+
url https://doi.org/10.1088/2632-2153/add853
work_keys_str_mv AT yaneli shufflewindowtransformerdeeplabv3alightweightconvolutionalneuralnetworkandtransformerbasedhybridsemanticsegmentationnetwork
AT zhichaochen shufflewindowtransformerdeeplabv3alightweightconvolutionalneuralnetworkandtransformerbasedhybridsemanticsegmentationnetwork
AT hongxiaqi shufflewindowtransformerdeeplabv3alightweightconvolutionalneuralnetworkandtransformerbasedhybridsemanticsegmentationnetwork
AT mingfan shufflewindowtransformerdeeplabv3alightweightconvolutionalneuralnetworkandtransformerbasedhybridsemanticsegmentationnetwork
AT lihuali shufflewindowtransformerdeeplabv3alightweightconvolutionalneuralnetworkandtransformerbasedhybridsemanticsegmentationnetwork