Enhancing Object Segmentation via Few-Shot Learning with Limited Annotated Data

Date

2024-11-20

Advisors

Journal Title

Journal ISSN

ISSN

2367-3370
2367-3389

Volume Title

Publisher

Springer Nature

Type

Book chapter

Peer reviewed

Yes

Abstract

Significant advancements in machine learning in recent years have revolutionized multiple sectors. The Segment-Anything Model (SAM) is a notable example of state-of-the-art image segmentation. Despite claims of zero-shot generalization, SAM exhibits limitations in specific scenarios like medical mammography images. SAM generates three segmentation masks per image to address this and recommends selecting the one with the highest confidence score. However, this is not always the optimal choice. This paper introduces a system that extends SAM’s segmentation capabilities by automatically selecting the correct mask, leveraging few-shot learning methods and an Out-of-Distribution threshold strategy. Several backbones were subjected to experimentation, highlighting the relationship between the support set size and the model’s accuracy.

Description

Keywords

Citation

García-Aguilar, I., Ali Haider Jafri, S., Elizondo, D., Calderón, S., Greenfield, S., M. Luque-Baena, R. (2025) Enhancing Object Segmentation via Few-Shot Learning with Limited Annotated Data. In: Quintián, H., et al. The 19th International Conference on Soft Computing Models in Industrial and Environmental Applications SOCO 2024. SOCO 2024. Lecture Notes in Networks and Systems, vol 889. Springer, Cham

Rights

Research Institute

Institute of Digital Research, Communication and Responsible Innovation