Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples

Few-shot segmentation (FSS) aims to segment a query image with a few support images. However, there can be large differences between images from the same category, and similarities between different categories, making it a challenging task. In addition, most FSS methods use powerful encoders to extr...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng Guo, Dong Zhou
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/7/3627
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850184640774537216
author Feng Guo
Dong Zhou
author_facet Feng Guo
Dong Zhou
author_sort Feng Guo
collection DOAJ
description Few-shot segmentation (FSS) aims to segment a query image with a few support images. However, there can be large differences between images from the same category, and similarities between different categories, making it a challenging task. In addition, most FSS methods use powerful encoders to extract features from the training class, which makes the model pay more attention to the features of the ‘seen’ class, and perform poorly on the segmentation task of ‘unseen’ classes. In this work, we propose a novel end-to-end model, called GFormer. GFormer has four components: encoder, prototype extractor, adversarial prototype generator, and decoder. Our encoder makes simple modifications to VIT to reduce the focus on image content, using a prototype extractor to extract prototype features from a range of support images. We further introduce different classes that are similar to the support image categories as negative examples, taking the support image categories as positive examples. We use the adversarial prototype generator to extract the adversarial prototypes from the positive and negative examples. The decoder segments the query images under the guidance of the prototypes. We conduct extensive experiments on a variety of unknown classes. The results verify the feasibility of the proposed model and prove that the proposed model has strong generalization performance for new classes.
format Article
id doaj-art-2e6202f771b04a818e2f803c77656cf9
institution OA Journals
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2e6202f771b04a818e2f803c77656cf92025-08-20T02:17:00ZengMDPI AGApplied Sciences2076-34172025-03-01157362710.3390/app15073627Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative ExamplesFeng Guo0Dong Zhou1Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, ChinaResearch Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, ChinaFew-shot segmentation (FSS) aims to segment a query image with a few support images. However, there can be large differences between images from the same category, and similarities between different categories, making it a challenging task. In addition, most FSS methods use powerful encoders to extract features from the training class, which makes the model pay more attention to the features of the ‘seen’ class, and perform poorly on the segmentation task of ‘unseen’ classes. In this work, we propose a novel end-to-end model, called GFormer. GFormer has four components: encoder, prototype extractor, adversarial prototype generator, and decoder. Our encoder makes simple modifications to VIT to reduce the focus on image content, using a prototype extractor to extract prototype features from a range of support images. We further introduce different classes that are similar to the support image categories as negative examples, taking the support image categories as positive examples. We use the adversarial prototype generator to extract the adversarial prototypes from the positive and negative examples. The decoder segments the query images under the guidance of the prototypes. We conduct extensive experiments on a variety of unknown classes. The results verify the feasibility of the proposed model and prove that the proposed model has strong generalization performance for new classes.https://www.mdpi.com/2076-3417/15/7/3627few-shot semantic segmentationprototype learningtransformer
spellingShingle Feng Guo
Dong Zhou
Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples
Applied Sciences
few-shot semantic segmentation
prototype learning
transformer
title Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples
title_full Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples
title_fullStr Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples
title_full_unstemmed Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples
title_short Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples
title_sort few shot semantic segmentation network for distinguishing positive and negative examples
topic few-shot semantic segmentation
prototype learning
transformer
url https://www.mdpi.com/2076-3417/15/7/3627
work_keys_str_mv AT fengguo fewshotsemanticsegmentationnetworkfordistinguishingpositiveandnegativeexamples
AT dongzhou fewshotsemanticsegmentationnetworkfordistinguishingpositiveandnegativeexamples