Latency driven spatially sparse optimization for multi-branch CNNs for semantic segmentation
Author(s)
Zampokas, Georgios
Bouganis, Christos-Savvas
Tzovaras, Dimitrios
Type
Conference Paper
Abstract
Semantic segmentation has gained significant attention in the field of computer vision, especially in the context of autonomous driving. Achieving superior performance and precise object localization is paramount for safe and reliable autonomous vehicles. This introduces the need to process high-resolution feature maps, resulting in increased computational requirements. Recently proposed multi-branch architectures address that by maintaining parallel computationally light high-resolution representations throughout the whole network. Since individual branches focus on different image regions by design, we believe that there is significant number of redundant computations, especially in high-resolution branches. To harness that, we propose a optimization scheme for multi-branch CNNs, which introduces spatial sparsity to the network to produce more efficient distribution of calculations. The proposed approach departs from the literature by introducing the actuallatency in the optimization process, resulting in device-tailored and practically-efficient sparse architectures.
Date Issued
2024-04-16
Date Acceptance
2024-01-01
Citation
2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2024, pp.949-957
ISBN
979-8-3503-7071-3
ISSN
2572-4398
Publisher
IEEE Computer Soc
Start Page
949
End Page
957
Journal / Book Title
2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)
Copyright Statement
© 2024 IEEE. This WACV workshop paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.
Source
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Subjects
Computer Science
Computer Science, Artificial Intelligence
Computer Science, Interdisciplinary Applications
Engineering
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Science & Technology
Technology
Publication Status
Published
Start Date
2024-01-01
Finish Date
2024-01-06
Coverage Spatial
Waikoloa, HI, USA