Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous Vehicles
Applications such as autonomous driving demand real-time and high-precision instance segmentation to accurately identify and understand objects in an environment, including pedestrians, vehicles, and traffic signs. Ensuring a balance between accuracy and efficiency in instance segmentation systems i...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | World Electric Vehicle Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2032-6653/16/1/8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587307254808576 |
|---|---|
| author | Aya Taourirte Li-Hong Juang |
| author_facet | Aya Taourirte Li-Hong Juang |
| author_sort | Aya Taourirte |
| collection | DOAJ |
| description | Applications such as autonomous driving demand real-time and high-precision instance segmentation to accurately identify and understand objects in an environment, including pedestrians, vehicles, and traffic signs. Ensuring a balance between accuracy and efficiency in instance segmentation systems is critical for such tasks. Traditional convolutional models face limitations in capturing complex features and global context effectively. To address these challenges, we propose an enhanced QueryInst-based instance segmentation framework. First, we replace the traditional CNN backbone with the DaViT Transformer to extract richer, multi-scale features. Next, we integrate Feature Pyramid Network CARAFE to capture global context and recover missed instances. Finally, we incorporate the Complete IoU (CIoU) loss function to optimize object localization and improve prediction accuracy. Experiments on the Cityscapes and COCO datasets demonstrate that our approach achieves mIoU scores of 46.7% and AP score of 45.5%, representing improvements of 6.1% and 2.6% over the baseline, respectively, outperforming other state-of-the-art methods. |
| format | Article |
| id | doaj-art-aaee2ea294e44cc38e197c3375b5f5fc |
| institution | Kabale University |
| issn | 2032-6653 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World Electric Vehicle Journal |
| spelling | doaj-art-aaee2ea294e44cc38e197c3375b5f5fc2025-01-24T13:52:44ZengMDPI AGWorld Electric Vehicle Journal2032-66532024-12-01161810.3390/wevj16010008Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous VehiclesAya Taourirte0Li-Hong Juang1School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaApplications such as autonomous driving demand real-time and high-precision instance segmentation to accurately identify and understand objects in an environment, including pedestrians, vehicles, and traffic signs. Ensuring a balance between accuracy and efficiency in instance segmentation systems is critical for such tasks. Traditional convolutional models face limitations in capturing complex features and global context effectively. To address these challenges, we propose an enhanced QueryInst-based instance segmentation framework. First, we replace the traditional CNN backbone with the DaViT Transformer to extract richer, multi-scale features. Next, we integrate Feature Pyramid Network CARAFE to capture global context and recover missed instances. Finally, we incorporate the Complete IoU (CIoU) loss function to optimize object localization and improve prediction accuracy. Experiments on the Cityscapes and COCO datasets demonstrate that our approach achieves mIoU scores of 46.7% and AP score of 45.5%, representing improvements of 6.1% and 2.6% over the baseline, respectively, outperforming other state-of-the-art methods.https://www.mdpi.com/2032-6653/16/1/8dual attention transformerautonomous vehiclesinstance segmentationQueryInst |
| spellingShingle | Aya Taourirte Li-Hong Juang Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous Vehicles World Electric Vehicle Journal dual attention transformer autonomous vehicles instance segmentation QueryInst |
| title | Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous Vehicles |
| title_full | Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous Vehicles |
| title_fullStr | Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous Vehicles |
| title_full_unstemmed | Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous Vehicles |
| title_short | Query-Based Instance Segmentation with Dual Attention Transformer for Autonomous Vehicles |
| title_sort | query based instance segmentation with dual attention transformer for autonomous vehicles |
| topic | dual attention transformer autonomous vehicles instance segmentation QueryInst |
| url | https://www.mdpi.com/2032-6653/16/1/8 |
| work_keys_str_mv | AT ayataourirte querybasedinstancesegmentationwithdualattentiontransformerforautonomousvehicles AT lihongjuang querybasedinstancesegmentationwithdualattentiontransformerforautonomousvehicles |