Logo image
Back
Multi-scale prototype convolutional network for few-shot semantic segmentation
Journal article   Open access   Peer reviewed

Multi-scale prototype convolutional network for few-shot semantic segmentation

Ding Xu, Shun Yu, Jingxuan Zhou, Fusen Guo, Lin Li and Jishizhan Chen
PloS one, Vol.20(4), pp.1-16
15/04/2025
DOI: https://doi.org/10.1371/journal.pone.0319905
PMID: 40233318
Appears in  Recent Faculty of Science and Engineering Publications
pdf
Multi-scale prototype convolutional network7.47 MBDownloadView
Published (Version of record)CC BY V4.0,  Open Access
url
Multi-scale prototype convolutional networkView
Published (Version of record)CC BY V4.0,  Open

Related links

Metrics

1 File views/ downloads
15 Record Views
1 Times Cited - Web of Science

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

Source: InCites

Abstract

Few-shot semantic segmentation aims to accurately segment objects from a limited amount of annotated data, a task complicated by intra-class variations and prototype representation challenges. To address these issues, we propose the Multi-Scale Prototype Convolutional Network (MPCN). Our approach introduces a Prior Mask Generation (PMG) module, which employs dynamic kernels of varying sizes to capture multi-scale object features. This enhances the interaction between support and query features, thereby improving segmentation accuracy. Additionally, we present a Multi-Scale Prototype Extraction (MPE) module to overcome the limitations of MAP (Mean Average Precision). By augmenting support set features, assessing spatial importance, and utilizing multi-scale downsampling, we obtain a more accurate prototype set. Extensive experiments conducted on the PASCAL-[Formula: see text] and COCO-[Formula: see text] datasets demonstrate that our method achieves superior performance in both 1-shot and 5-shot settings.

Details

Logo image