Semi-supervised instance segmentation algorithm based on transfer learning

Semi-supervised instance segmentation algorithms are mainly divided into algorithms based on pseudo-label generation and algorithms based on transfer learning. The algorithms based on pseudo-label generation need to design a specific pseudo-label generation process, but the process is not scalable f...

Full description

Saved in:
Bibliographic Details
Published in:Nondestructive testing and evaluation Vol. 39; no. 1; pp. 185 - 203
Main Authors: Liu, Bing, Yi, Ren, Yu, Zhongquan, Wang, Shiyu, Yang, Xuewen, Wang, Fuwen
Format: Journal Article
Language:English
Published: Abingdon Taylor & Francis 02.01.2024
Taylor & Francis Ltd
Subjects:
Algorithms
Instance segmentation
Knowledge management
Labels
Machine learning
Semi-supervised learning
transfer learning
ISSN:1058-9759, 1477-2671
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Semi-supervised instance segmentation algorithms are mainly divided into algorithms based on pseudo-label generation and algorithms based on transfer learning. The algorithms based on pseudo-label generation need to design a specific pseudo-label generation process, but the process is not scalable for different types of source tasks. The algorithms based on transfer learning that started late have relatively high scalability, but the algorithm research ideas are relatively simple. To expand the research on semi-supervised instance segmentation based on transfer learning, this paper proposes a feature transfer-based semi-supervised instance segmentation algorithm Feature Transfer Mask R-CNN (FT-Mask). The FT-Mask algorithm is more scalable than algorithms based on pseudo-label generation and can be used to transfer knowledge from different types of source tasks. Compared with other semi-supervised instance segmentation algorithms based on transfer learning, FT-Mask uses the feature transfer method to achieve semi-supervised instance segmentation for the first time. The experimental results show that the FT-Mask model improves the semi-supervised instance segmentation accuracy of the Mask R-CNN benchmark model through the semi-supervised learning process, and can achieve effective transfer learning.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1058-9759
1477-2671
DOI:10.1080/10589759.2023.2274013