Self-support prototype-aware for few-shot semantic segmentation

Publication Type

Conference Proceeding Article

Publication Date

4-2025

Abstract

In recent years, significant progress has been made in prototype-based learning methods for few-shot semantic segmentation. However, prototype features originating from the support images are interfered with by intra-class diversity and thus cannot be aligned with the query foreground, resulting in poor segmentation accuracy. Therefore, we propose a novel self-support prototype-aware (SSPA) network to obtain highly confident query foreground pixel points and their corresponding query features. We design Cycle Consistency Collection module and Self-Support Collection module to address the interference of invalid support prototypes. Experimental results demonstrate that our SSPA significantly improves the quality of prototypes and achieves state-of-the-art segmentation results on multiple datasets. In particular, SSPA achieves mIoU scores of 69.7% and 76.4% for 1-shot and 5-shot segmentation, respectively, on PASCAL-5i.

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Publication

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, April 6-11

Identifier

10.1109/ICASSP49660.2025.10890480

Publisher

IEEE

City or Country

Pistacataway

Additional URL

https://doi.org/10.1109/ICASSP49660.2025.10890480

This document is currently not available here.

Share

COinS