Detail View

Video Instance Segmentation using Knowledge Distillation
Citations

WEB OF SCIENCE

Citations

SCOPUS

Metadata Downloads

Title
Video Instance Segmentation using Knowledge Distillation
DGIST Authors
Hojin KimSunghoon ImKyong Hwan Jin
Advisor
임성훈
Co-Advisor(s)
Kyong Hwan Jin
Issued Date
2023
Awarded Date
2023-02-01
Citation
Hojin Kim. (2023). Video Instance Segmentation using Knowledge Distillation. doi: 10.22677/THESIS.200000653859
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
DOI
10.22677/THESIS.200000653859
Degree
Master
Department
Department of Electrical Engineering and Computer Science
Publisher
DGIST
Show Full Item Record

File Downloads

  • There are no files associated with this item.

공유

qrcode
공유하기

Total Views & Downloads