준지도 학습 기반의 미세조직 이미지 분할 = Image Segmentation for Microstructure based on Semi-supervised Learning

다국어 초록 (Multilingual Abstract)

In order to solve problems such as data collection and expensive labeling work, we proposed an image segmentation model using semi-supervised and unsupervised learning methods. Since semi-supervised learning is used, high performance can be achieved even in situations with little ground truth. The proposed model consists of a segmentation module and a cluster module. The Segment Anything Model (SAM) is used for the segmentation module. The cluster module uses the k-means clustering algorithm, a representative method of unsupervised learning, to determine whether components belong to the same class within the microbial image. Finally, by configuring a user interface, the system was created to return all objects and corresponding components belonging to the same cluster when the user selects an element that wants to be divided. Both the segmentation module and the cluster module can use semi-supervised or unsupervised learning to reduce the cost of work such as data collection and labeling, which has been a problem with the existing image segmentation model.

참고문헌 (Reference)

1 M. Zheng, "Simmatch: Semi-supervised Learning with Similarity Matching" 14471-14481, 2022

2 A. Kirillov, "Segment Anything" 4015-4026, 2023

3 T. M. Kodinariya, "Review on Determining Number of Cluster in K-Means Clustering" 1 (1): 90-95, 2013

4 Y. J. Lee, "Image Segmentation Based on Semi-Supervised Learning" 35-37, 2024

5 B. Zhang, "Flexmatch : Boosting Semi-supervised Learning with Curriculum Pseudo Labeling" 34 : 18408-18419, 2021

6 K. Sohn, "Fixmatch : Simplifying Semi-supervised Learning with Consistency and Confidence" 33 : 596-608, 2020

7 T. Kanungo, "An Efficient K-means Clustering Algorithm: Analysis and Implementation" 24 (24): 881-892, 2002

8 J. E. Van Engelen, "A Survey on Semi-supervised Learning" 109 (109): 373-440, 2020

9 W. Shen, "A Survey on Label-Efficient Deep Image Segmentation : Bridging the Gap Between Weak Supervision and Dense Prediction" 45 (45): 9284-9305, 2023

10 X. Yang, "A Survey on Deep Semi-supervised Learning" 35 (35): 8934-8954, 2022