Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 6, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

886

AutoMamba: Efficient Autonomous Driving Segmentation Model with Mamba.

Haoran Sun1, Zhensong Li1, Shiliang Zhu2

  • 1School of Information and Communication Engineering, The Center for Target Cognition Information Processing Science and Technology, Beijing Information Science and Technology University, Beijing 102206, China.

Sensors (Basel, Switzerland)
|April 14, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Hierarchy of Motor Control01:18

Hierarchy of Motor Control

5.6K
The hierarchy of motor control refers to the different levels of organization and processing involved in controlling movement in the body. These levels range from higher cortical areas involved in planning and decision-making to lower spinal cord reflexes that respond automatically to external stimuli.
5.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

RTMF-Net: A Dual-Modal Feature-Aware Fusion Network for Dense Forest Object Detection.

Sensors (Basel, Switzerland)·2025
Same author

Lightweight high-precision SAR ship detection method based on YOLOv7-LDS.

PloS one·2024
Same author

Delay-Informed Intelligent Formation Control for UAV-Assisted IoT Application.

Sensors (Basel, Switzerland)·2023
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

AutoMamba, a novel Hybrid-SSM architecture, enhances semantic segmentation for autonomous driving by efficiently processing high-resolution data. It achieves superior performance and scalability compared to Transformers, addressing limitations of existing State Space Models.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Deep Learning Architectures

Background:

  • Semantic segmentation for autonomous driving requires balancing high-fidelity perception with real-time performance.
  • Transformers offer state-of-the-art results but face quadratic complexity issues with high-resolution images.
  • State Space Models (SSMs) like Mamba provide linear complexity but struggle with local detail loss and inefficient scanning.

Purpose of the Study:

  • To introduce AutoMamba, a Hybrid-SSM architecture designed for efficient and accurate semantic segmentation in autonomous driving.
  • To address the limitations of existing Transformers and SSMs in processing high-resolution data and capturing local details.

Main Methods:

  • Developed a Hybrid-SSM block integrating Depthwise Convolutions for local spatial priors.
Keywords:
autonomous drivinglinear complexitymambareal-time perceptionsemantic segmentationstate space models (SSM)

Related Experiment Videos

Last Updated: May 6, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

886
  • Implemented a Stage-Adaptive Mixed-Scanning strategy prioritizing horizontal context and selectively using vertical scanning.
  • Incorporated Auxiliary Supervision and Online Hard Example Mining (OHEM) to mitigate 'long-tail forgetting' in Mamba architectures.

    • Main Results:

    • AutoMamba demonstrated superior performance on Cityscapes and BDD100K datasets in a training-from-scratch setting.
    • AutoMamba-B0 achieved 67.79% mIoU on Cityscapes with 31.3% fewer FLOPs than SegFormer-B0.
    • AutoMamba-B2 efficiently scaled to 2048x2048 resolution, unlike SegFormer-B2 which encountered Out-Of-Memory errors.

    Conclusions:

    • AutoMamba offers a compelling alternative for high-resolution semantic segmentation in autonomous driving.
    • The proposed architecture effectively balances perception fidelity with computational efficiency.
    • AutoMamba's linear complexity advantage positions it for next-generation perception systems.