Semi-supervised tooth instance segmentation
Tooth segmentation is getting popular with the development of 3D computer vision technology. Current tooth segmentation models rely on large annotations of data which requires great effort from experts and increases the computation cost for training. In this report we proposed to implement mea...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176834 |
| _version_ | 1826123826426019840 |
|---|---|
| author | Ling, Zijie |
| author2 | Jiang Xudong |
| author_facet | Jiang Xudong Ling, Zijie |
| author_sort | Ling, Zijie |
| collection | NTU |
| description | Tooth segmentation is getting popular with the development of 3D computer vision
technology. Current tooth segmentation models rely on large annotations of data which
requires great effort from experts and increases the computation cost for training. In this
report we proposed to implement mean teacher, a semi-supervised learning framework to
train the tooth instance segmentation model. Our experiment results shows that our
network can achieve comparable performance with fully supervised network but requires
far less data annotation and computation cost. |
| first_indexed | 2024-10-01T06:10:41Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/176834 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:10:41Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1768342024-05-24T15:43:29Z Semi-supervised tooth instance segmentation Ling, Zijie Jiang Xudong School of Electrical and Electronic Engineering Institute for Infocomm Research (I2R) Yang Xulei EXDJiang@ntu.edu.sg Engineering Semi-supervision Tooth instance segmentation Tooth segmentation is getting popular with the development of 3D computer vision technology. Current tooth segmentation models rely on large annotations of data which requires great effort from experts and increases the computation cost for training. In this report we proposed to implement mean teacher, a semi-supervised learning framework to train the tooth instance segmentation model. Our experiment results shows that our network can achieve comparable performance with fully supervised network but requires far less data annotation and computation cost. Bachelor's degree 2024-05-21T02:12:19Z 2024-05-21T02:12:19Z 2024 Final Year Project (FYP) Ling, Z. (2024). Semi-supervised tooth instance segmentation. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/176834 https://hdl.handle.net/10356/176834 en B3074-231 application/pdf Nanyang Technological University |
| spellingShingle | Engineering Semi-supervision Tooth instance segmentation Ling, Zijie Semi-supervised tooth instance segmentation |
| title | Semi-supervised tooth instance segmentation |
| title_full | Semi-supervised tooth instance segmentation |
| title_fullStr | Semi-supervised tooth instance segmentation |
| title_full_unstemmed | Semi-supervised tooth instance segmentation |
| title_short | Semi-supervised tooth instance segmentation |
| title_sort | semi supervised tooth instance segmentation |
| topic | Engineering Semi-supervision Tooth instance segmentation |
| url | https://hdl.handle.net/10356/176834 |
| work_keys_str_mv | AT lingzijie semisupervisedtoothinstancesegmentation |