Video Instance Segmentation using Knowledge Distillation
- Title
- Video Instance Segmentation using Knowledge Distillation
- Author(s)
- Hojin Kim
- DGIST Authors
- Hojin Kim ; Sunghoon Im ; Kyong Hwan Jin
- Advisor
- 임성훈
- Co-Advisor(s)
- Kyong Hwan Jin
- Issued Date
- 2023
- Awarded Date
- 2023-02-01
- Type
- Thesis
- Description
- Video Instance Segmentation (VIS), Knowledge Distillation
- Table Of Contents
-
I. Introduction 1
II. Related Work 3
III. Proposed method 4
3.1 Online VIS model 5
3.2 Offline Knowledge Extraction 5
3.3 Offline-to-Online Knowledge Distillation 6
3.4 Minor-Paste 7
IV. Experiments 8
4.1 Experimental Setup 8
4.2 Comparison to State-of-the-art Methods 9
4.3 Ablation Study 12
V. Conclusion 16
VI. References 17
VII. 요약문 22
- URI
-
http://hdl.handle.net/20.500.11750/45752
http://dgist.dcollection.net/common/orgView/200000653859
- Degree
- Master
- Publisher
- DGIST
- Related Researcher
-
-
Im, Sunghoon
- Research Interests Computer Vision; Deep Learning; Robot Vision
-
- Files in This Item:
-
There are no files associated with this item.
- Appears in Collections:
- Department of Electrical Engineering and Computer Science Theses Master
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.