SEP: stage-enhanced panoptic segmentation based on fully convolutional networks

Shucheng Ji; Xiaochen Yuan; Junqi Bao

doi:10.1117/12.3023068

28 March 2024 SEP: stage-enhanced panoptic segmentation based on fully convolutional networks

Shucheng Ji, Xiaochen Yuan, Junqi Bao

Proceedings Volume 13091, Fifteenth International Conference on Signal Processing Systems (ICSPS 2023); 130911X (2024) https://doi.org/10.1117/12.3023068
Event: Fifteenth International Conference on Signal Processing Systems (ICSPS 2023), 2023, Xi’an, China

Abstract

Panoptic segmentation is a critical technology in the field of multimedia, applicable to various domains such as autonomous driving and image recognition. However, due to the enormity and complexity of the task, enhancing the efficiency and accuracy of panoptic segmentation remains a challenge. In this paper, we propose a stage-enhanced panoptic segmentation method which improves the feature extraction network of the backbone, incorporates a stage feature fusion network, and designs a module for adaptive stage feature weight allocation. These enhancements optimize the overall network and enrich the stage features. Experimental results on the publicly available COCO-2017 dataset confirm the performance of Stage-Enhanced Panoptic and demonstrate its superiority compared to other methods.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shucheng Ji, Xiaochen Yuan, and Junqi Bao "SEP: stage-enhanced panoptic segmentation based on fully convolutional networks", Proc. SPIE 13091, Fifteenth International Conference on Signal Processing Systems (ICSPS 2023), 130911X (28 March 2024); https://doi.org/10.1117/12.3023068

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available