Weakly Supervised Few-Shot Segmentation via Meta-Learning

Semantic segmentation is a classic computer vision task with multiple applications, which includes medical and remote sensing image analysis. Despite recent advances with deep-based approaches, labeling samples (pixels) for training models is laborious and, in some cases, unfeasible. In this paper,...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on multimedia Vol. 25; pp. 1784 - 1797
Main Authors Gama, Pedro H. T., Oliveira, Hugo, Junior, Jose Marcato, Santos, Jefersson A. dos
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Agriculture
Annotations
Biomedical imaging
Computer vision
few-shot
Image analysis
Image annotation
Image segmentation
Learning
Medical imaging
medical imaging analysis
meta learning
Prototypes
Remote sensing
Semantic segmentation
Semantics
Task analysis
Training
weakly supervised
Online AccessGet full text

Cover

More Information
Summary:Semantic segmentation is a classic computer vision task with multiple applications, which includes medical and remote sensing image analysis. Despite recent advances with deep-based approaches, labeling samples (pixels) for training models is laborious and, in some cases, unfeasible. In this paper, we present two novel meta-learning methods, named WeaSeL and ProtoSeg, for the few-shot semantic segmentation task with sparse annotations. We conducted an extensive evaluation of the proposed methods in different applications (12 datasets) in medical imaging and agricultural remote sensing, which are very distinct fields of knowledge and usually subject to data scarcity. The results demonstrated the potential of our method, achieving suitable results for segmenting both coffee/orange crops and anatomical parts of the human body in comparison with full dense annotation.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2022.3162951