Few-Shot Segmentation Using Multi-Similarity and Attention Guidance

Few-Shot Segmentation Using Multi-Similarity and Attention Guidance

Few-shot segmentation (FSS) methods aim to segment objects of novel classes with relatively few annotated samples. Prototype learning, a popular approach in FSS, employs prototype vectors to transfer information from known classes (support images) to novel classes(query images) for segmentation. How...

Full description

Saved in:
Bibliographic Details
Main Authors: Ehtesham Iqbal, Sirojbek Safarov, Seongdeok Bang, Sajid Javed, Yahya Zweiri, Yusra Abdulrahman
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Computer Society
Subjects:
Few-shot learning
Image segmentation
Deep learning
Online Access:https://ieeexplore.ieee.org/document/11095423/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Few-shot segmentation (FSS) methods aim to segment objects of novel classes with relatively few annotated samples. Prototype learning, a popular approach in FSS, employs prototype vectors to transfer information from known classes (support images) to novel classes(query images) for segmentation. However, using only prototype vectors may not be sufficient to represent all features of the support image. To extract abundant features and make more precise predictions, we propose a <bold>M</bold>ulti-<bold>S</bold>imilarity and <bold>A</bold>ttention <bold>N</bold>etwork (MSANet) including two novel modules, a multi-similarity module and an attention module. The multi-similarity module exploits multiple feature-map of support images and query images to estimate accurate semantic relationships. The attention module instructs the MSANet to concentrate on class-relevant information. We evaluated the proposed network on standard FSS datasets, PASCAL-<inline-formula><tex-math notation="LaTeX">$5^{i}$</tex-math></inline-formula> 1-shot, PASCAL-<inline-formula><tex-math notation="LaTeX">$5^{i}$</tex-math></inline-formula> 5-shot, COCO-<inline-formula><tex-math notation="LaTeX">$20^{i}$</tex-math></inline-formula> 1-shot, and COCO-<inline-formula><tex-math notation="LaTeX">$20^{i}$</tex-math></inline-formula> 5-shot. An MSANet model with a ResNet101 backbone achieved state-of-the-art performance for all four benchmark datasets with mean intersection over union (mIoU) values of 69.13&#x0025;, 73.99&#x0025;, 51.09&#x0025;, and 56.80&#x0025;, respectively. The code used is available at <uri>https://github.com/AIVResearch/MSANet</uri>.
ISSN:2644-1268

Similar Items