Improved MaskFormer visual target segmentation method for noisy interference images

Yuanjin Sun; Gang Li; Pengbo Li; Ling Zhang; Shujing An; Jingkun Cao

doi:10.1117/12.3044886

9 October 2024 Improved MaskFormer visual target segmentation method for noisy interference images

Yuanjin Sun, Gang Li, Pengbo Li, Ling Zhang, Shujing An, Jingkun Cao

Proceedings Volume 13288, Fourth International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2024); 132880U (2024) https://doi.org/10.1117/12.3044886
Event: Fourth International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2024), 2024, Chengdu, China

Abstract

Aiming at the problem that the image is defaced with more noise and complex features that make the target difficult to be segmented accurately, the traditional CNN target segmentation method is difficult to fully extract the detail information. Based on this, a segmentation network based on improved MaskFormer is proposed in this paper. The lightweight mask attention mechanism is used instead of the Transformer decoding attention mechanism, and the foreground region of each prediction mask is constrained by cross-attention, which reduces the interference of the smeared region and enhances the extraction of local features; GAMS, a multi-scale feature fusion module based on the gating mechanism, is used to carve out the semantic information of the image at different scales, which improves the feature discriminative ability of the model; the exchange of the self-attention and the lightweight mask attention order to reduce the network computation and improve the model training efficiency. The optimal values of evaluation indexes such as MIoU, ssMIoU and msMIoU are obtained in the segmentation experiments on ADE20K and COCO-Stuff-10k datasets after noise defacement treatment, and the improved MaskFormer segmentation performance is better compared with other networks.

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

Citation Download Citation

Yuanjin Sun, Gang Li, Pengbo Li, Ling Zhang, Shujing An, and Jingkun Cao "Improved MaskFormer visual target segmentation method for noisy interference images", Proc. SPIE 13288, Fourth International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2024), 132880U (9 October 2024); https://doi.org/10.1117/12.3044886

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

Image segmentation

Transformers

Data modeling

Feature fusion

Semantics

Education and training

Feature extraction

Show All Keywords

Keywords/Phrases

Search In:

Publication Years