Work

Judging From Support-Set: A New Way To Utilize Few-Shot Segmentation For Segmentation Refinement Process

Year: 2025

Type: conference-paper

Abstract: Segmentation refinement enhances coarse masks generated by segmentation algorithms, aiming for detailed and accurate contours of target objects. Despite advancements in segmentation refinement research, no method exists to evaluate its success, which is critical for reliable applications. To address this gap, we propose Judging From Support-set (JFS), leveraging a few-shot segmentation (FSS) model in a novel evaluation pipeline. Traditional FSS aims to locate target objects in query images using support set information. In JFS, coarse and refined masks from segmentation refinement methods become support masks for the FSS model, with the existing support mask serving as the test set. This setup evaluates the quality of refined segmentation. We validate JFS using the SAM Enhanced Pseudo-Labels (SEPL) and SegGPT on the PASCAL dataset, demonstrating its potential to reliably judge segmentation refinement success and foster innovation in image processing.

Source: Proceedings - International Conference on Image Processing

DOI: 10.1109/icip55913.2025.11084668

Authors: Seonghyeon Moon, Qingze Tony Liu, Haein Kong, Muhammad Haris Khan

Institutions: Brookhaven National Laboratory, Rutgers, The State University of New Jersey, Mohamed bin Zayed University of Artificial Intelligence

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: U.S. Department of Energy, National Energy Research Scientific Computing Center

OpenAlex ID: W4413277995

FWCI:

Cites: 20

Cited by:

Related to: 10