Pseudo-label based and transformation-consistent self-ensembling model for underwater life images

Shan Huang; Xiaonan Luo; Jiahao Lu; Chao Huang; Chengpei Xu; Tianran Yuan

doi:10.1117/12.2681247

8 June 2023 Pseudo-label based and transformation-consistent self-ensembling model for underwater life images

Shan Huang, Xiaonan Luo, Jiahao Lu, Chao Huang, Chengpei Xu, Tianran Yuan

Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 1270752 (2023) https://doi.org/10.1117/12.2681247
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China

Abstract

With the continuous development of underwater vision technology, high-precision object segmentation has received more attention from scholars. Due to the complexity of the underwater environment, the segmentation of underwater objects has become a new challenge. In order to alleviate such problems, this paper proposes a semi-supervised segmentation model based on pseudo-labels and transformation-consistent(PSTM). Due to the complexity of underwater images, PSTM preprocesses underwater biological images through an image enhancement module. A semi-supervised segmentation network with pseudo-labels and transformation-consistent is then used to obtain a more robust segmentation result. The method in this paper achieves better performance on the public underwater biological dataset DUT-USEG.

Citation Download Citation

Shan Huang, Xiaonan Luo, Jiahao Lu, Chao Huang, Chengpei Xu, and Tianran Yuan "Pseudo-label based and transformation-consistent self-ensembling model for underwater life images", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 1270752 (8 June 2023); https://doi.org/10.1117/12.2681247

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image segmentation

Data modeling

Image enhancement

Education and training

Image quality

Performance modeling

Neural networks

Show All Keywords

Keywords/Phrases

Search In:

Publication Years