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:
Online Access:https://ieeexplore.ieee.org/document/11095423/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762079675777024
author Ehtesham Iqbal
Sirojbek Safarov
Seongdeok Bang
Sajid Javed
Yahya Zweiri
Yusra Abdulrahman
author_facet Ehtesham Iqbal
Sirojbek Safarov
Seongdeok Bang
Sajid Javed
Yahya Zweiri
Yusra Abdulrahman
author_sort Ehtesham Iqbal
collection DOAJ
description 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>.
format Article
id doaj-art-fef0e45fa1a2489ebb5de2d3a90091a1
institution DOAJ
issn 2644-1268
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Computer Society
spelling doaj-art-fef0e45fa1a2489ebb5de2d3a90091a12025-08-20T03:05:50ZengIEEEIEEE Open Journal of the Computer Society2644-12682025-01-0161271128210.1109/OJCS.2025.359229111095423Few-Shot Segmentation Using Multi-Similarity and Attention GuidanceEhtesham Iqbal0https://orcid.org/0000-0003-1798-036XSirojbek Safarov1https://orcid.org/0000-0001-5724-3271Seongdeok Bang2https://orcid.org/0009-0003-1745-3217Sajid Javed3https://orcid.org/0000-0002-0036-2875Yahya Zweiri4https://orcid.org/0000-0003-4331-7254Yusra Abdulrahman5https://orcid.org/0000-0003-1211-8498Advanced Research and Innovation Center (ARIC), Khalifa University of Science and Technology, Abu Dhabi, UAEAiV Research Group, Yusung-ku, South KoreaAiV Research Group, Yusung-ku, South KoreaDepartment of Computer Science, Khalifa University of Science and Technology, Abu Dhabi, UAEAdvanced Research and Innovation Center (ARIC), Khalifa University of Science and Technology, Abu Dhabi, UAEAdvanced Research and Innovation Center (ARIC), Khalifa University of Science and Technology, Abu Dhabi, UAEFew-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>.https://ieeexplore.ieee.org/document/11095423/Few-shot learningImage segmentationDeep learning
spellingShingle Ehtesham Iqbal
Sirojbek Safarov
Seongdeok Bang
Sajid Javed
Yahya Zweiri
Yusra Abdulrahman
Few-Shot Segmentation Using Multi-Similarity and Attention Guidance
IEEE Open Journal of the Computer Society
Few-shot learning
Image segmentation
Deep learning
title Few-Shot Segmentation Using Multi-Similarity and Attention Guidance
title_full Few-Shot Segmentation Using Multi-Similarity and Attention Guidance
title_fullStr Few-Shot Segmentation Using Multi-Similarity and Attention Guidance
title_full_unstemmed Few-Shot Segmentation Using Multi-Similarity and Attention Guidance
title_short Few-Shot Segmentation Using Multi-Similarity and Attention Guidance
title_sort few shot segmentation using multi similarity and attention guidance
topic Few-shot learning
Image segmentation
Deep learning
url https://ieeexplore.ieee.org/document/11095423/
work_keys_str_mv AT ehteshamiqbal fewshotsegmentationusingmultisimilarityandattentionguidance
AT sirojbeksafarov fewshotsegmentationusingmultisimilarityandattentionguidance
AT seongdeokbang fewshotsegmentationusingmultisimilarityandattentionguidance
AT sajidjaved fewshotsegmentationusingmultisimilarityandattentionguidance
AT yahyazweiri fewshotsegmentationusingmultisimilarityandattentionguidance
AT yusraabdulrahman fewshotsegmentationusingmultisimilarityandattentionguidance