Title

Incremental Learning to Segment Multiple Organs Using DeepInversion

DGIST Authors

Jihyeon Kim ; Sanghyun Park ; Okkyun Lee

Advisor

박상현

Co-Advisor(s)

Okkyun Lee

Issued Date

2024

Awarded Date

2024-08-01

Citation

Jihyeon Kim. (2024). Incremental Learning to Segment Multiple Organs Using DeepInversion. doi: 10.22677/THESIS.200000802008

Type

Thesis

Description

Incremental learning, Multi-organ segmentation, DeepInversion

Table Of Contents

Contents i
List of Tables ii
List of Figures iii
I. INTRODUCTION 1
II. RELATED WORKS 4
1 Distillation-based methods 4
2 Rehearsal-based Methods 5
3 Data-Free Methods 6
III. Method 7
1 Notation 7
2 Framework of Incremental Learning 8
2.1 Segmentation Loss 9
2.2 Distillation Loss 10
3 Generation of Fake Images with MOSInversion 10
IV. RESULTS 13
1 Dataset 13
2 Implementation details 13
3 Evaluation 14
3.1 Results 14
3.2 The effect of the quality of generated images on model performance 16
3.3 The effect of the learning sequence 20
V. CONCLUSION 22
References 23
i

URI

http://hdl.handle.net/20.500.11750/57611
http://dgist.dcollection.net/common/orgView/200000802008

DOI

10.22677/THESIS.200000802008

Degree

Master

Department

Department of Robotics and Mechatronics Engineering

Publisher

DGIST

Show Full Item Record