A swin transformer-based asymmetrical network for light field salient object detection

Yunqing Li; Jiquan Ma

doi:10.1117/12.2689791

10 August 2023 A swin transformer-based asymmetrical network for light field salient object detection

Yunqing Li, Jiquan Ma

Proceedings Volume 12748, 5th International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2023); 127480S (2023) https://doi.org/10.1117/12.2689791
Event: 5th International Conference on Information Science, Electrical and Automation Engineering (ISEAE 2023), 2023, Wuhan, China

Abstract

In this paper, we propose a Swin Transformer-based Asymmetrical Network (SwinAN) for light field salient object detection (SOD). SwinAN is a bifurcated backbone network composed of a 2D branch and a 3D branch. The 2D branch is driven by Swin Transformer blocks for all-in-focus images, while the 3D branch is constructed by a 3D convolutional neural network (CNN) for focus stacks. Then, the high-level features extracted by the asymmetric backbone network are integrated using cascaded Multi-Level feature Fusion (MLF) modules, which consist of channel attention mechanisms and a residual block. Finally, the Multi-Attention Fusion (MAF) module is used to fuse multi-modal features to generate the predicted saliency maps. Experimental results show that after comparing 10 different SOD models, our SwinAN achieves excellent performance on 3 datasets, confirming the superiority as an efficient and accurate method for detecting saliency

Citation Download Citation

Yunqing Li and Jiquan Ma "A swin transformer-based asymmetrical network for light field salient object detection", Proc. SPIE 12748, 5th International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2023), 127480S (10 August 2023); https://doi.org/10.1117/12.2689791

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
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature fusion

Transformers

Feature extraction

Object detection

Data modeling

3D image processing

Ablation

Show All Keywords

Keywords/Phrases

Search In:

Publication Years