Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street Scenes
Semantic segmentation is a crucial technology for autonomous vehicles to acquire information about their surrounding environment. To ensure that semantic segmentation has practical application value in autonomous driving and robotics, it must achieve corresponding real-time inference speeds. However...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10813360/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563324491235328 |
|---|---|
| author | Baofeng Ye Renzheng Xue |
| author_facet | Baofeng Ye Renzheng Xue |
| author_sort | Baofeng Ye |
| collection | DOAJ |
| description | Semantic segmentation is a crucial technology for autonomous vehicles to acquire information about their surrounding environment. To ensure that semantic segmentation has practical application value in autonomous driving and robotics, it must achieve corresponding real-time inference speeds. However, existing models either improve accuracy at the cost of high computational expense and long inference times or enhance inference speed by sacrificing resolution and multi-level detailed information, resulting in a significant drop in accuracy. In this paper, we propose a new architecture based on a bilateral segmentation network, called DADNet. We have designed a new attention mechanism to optimize feature maps and a feature fusion module with an attention mechanism to efficiently merge different features, effectively expanding the receptive field. Our method demonstrates an excellent balance between segmentation accuracy and speed on the Cityscapes and CamVid datasets. Specifically, DADNet achieves a mIoU of 78.2% at 90.5 FPS on the Cityscapes validation set using a single 2080Ti GPU. On the CamVid test set, it achieves a mIoU of 75.8% at 136.7 FPS. Our approach outperforms most state-of-the-art models while requiring less computational power. |
| format | Article |
| id | doaj-art-d2fe1bb611054a2a8b90a42ab9a076a8 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d2fe1bb611054a2a8b90a42ab9a076a82025-01-03T00:01:57ZengIEEEIEEE Access2169-35362025-01-011358859510.1109/ACCESS.2024.352195810813360Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street ScenesBaofeng Ye0https://orcid.org/0009-0000-5651-4906Renzheng Xue1https://orcid.org/0009-0000-7183-4502School of Computer and Control Engineering, Qiqihar University, Qiqihar, ChinaKey Laboratory of Big Data Network Security Detection and Analysis, Qiqihar University, Qiqihar, Heilongjiang, ChinaSemantic segmentation is a crucial technology for autonomous vehicles to acquire information about their surrounding environment. To ensure that semantic segmentation has practical application value in autonomous driving and robotics, it must achieve corresponding real-time inference speeds. However, existing models either improve accuracy at the cost of high computational expense and long inference times or enhance inference speed by sacrificing resolution and multi-level detailed information, resulting in a significant drop in accuracy. In this paper, we propose a new architecture based on a bilateral segmentation network, called DADNet. We have designed a new attention mechanism to optimize feature maps and a feature fusion module with an attention mechanism to efficiently merge different features, effectively expanding the receptive field. Our method demonstrates an excellent balance between segmentation accuracy and speed on the Cityscapes and CamVid datasets. Specifically, DADNet achieves a mIoU of 78.2% at 90.5 FPS on the Cityscapes validation set using a single 2080Ti GPU. On the CamVid test set, it achieves a mIoU of 75.8% at 136.7 FPS. Our approach outperforms most state-of-the-art models while requiring less computational power.https://ieeexplore.ieee.org/document/10813360/Semantic segmentationattentionreal-timedeep learning |
| spellingShingle | Baofeng Ye Renzheng Xue Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street Scenes IEEE Access Semantic segmentation attention real-time deep learning |
| title | Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street Scenes |
| title_full | Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street Scenes |
| title_fullStr | Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street Scenes |
| title_full_unstemmed | Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street Scenes |
| title_short | Dual Attention Dual-Resolution Networks for Real-Time Semantic Segmentation of Street Scenes |
| title_sort | dual attention dual resolution networks for real time semantic segmentation of street scenes |
| topic | Semantic segmentation attention real-time deep learning |
| url | https://ieeexplore.ieee.org/document/10813360/ |
| work_keys_str_mv | AT baofengye dualattentiondualresolutionnetworksforrealtimesemanticsegmentationofstreetscenes AT renzhengxue dualattentiondualresolutionnetworksforrealtimesemanticsegmentationofstreetscenes |