Please use this identifier to cite or link to this item:
Title: Self-regularized prototypical network for few-shot semantic segmentation
Authors: Ding, Henghui 
Zhang, Hui
Jiang, Xudong
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2023
Source: Ding, H., Zhang, H. & Jiang, X. (2023). Self-regularized prototypical network for few-shot semantic segmentation. Pattern Recognition, 133, 109018-.
Journal: Pattern Recognition
Abstract: The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties in generalizing to unseen object categories. Therefore, few-shot segmentation has been developed to perform segmentation with just a few annotated examples. In this work, we tackle the few-shot segmentation using a self-regularized prototypical network (SRPNet) based on prototype extraction for better utilization of the support information. The proposed SRPNet extracts class-specific prototype representations from support images and generates segmentation masks for query images by a distance metric - the fidelity. A direct yet effective prototype regularization on support set is proposed in SRPNet, in which the generated prototypes are evaluated and regularized on the support set itself. The extent to which the generated prototypes restore the support mask imposes an upper limit on performance. The performance on the query set should never exceed the upper limit no matter how complete the knowledge is generalized from support set to query set. With the specific prototype regularization, SRPNet fully exploits knowledge from the support and offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. The query performance is further improved by an iterative query inference (IQI) module that combines a set of regularized prototypes. Our proposed SRPNet achieves new state-of-art performance on 1-shot and 5-shot segmentation benchmarks.
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2022.109018
Schools: School of Electrical and Electronic Engineering 
Rights: © 2022 Elsevier Ltd. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 20

Updated on Apr 19, 2024

Web of ScienceTM
Citations 20

Updated on Oct 30, 2023

Page view(s)

Updated on Apr 23, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.