Towards high-quality panoptic segmentation
Panoptic segmentation is a recently proposed task that unifies both instance and semantic segmentation. It provides a holistic solution to scene parsing by predicting instance labels and pixel-level classification. To improve the performance of our panoptic segmentation system, we explore various me...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/138017 |
| _version_ | 1826115998927814656 |
|---|---|
| author | Chen, Chongsong |
| author2 | Chen Change Loy |
| author_facet | Chen Change Loy Chen, Chongsong |
| author_sort | Chen, Chongsong |
| collection | NTU |
| description | Panoptic segmentation is a recently proposed task that unifies both instance and semantic segmentation. It provides a holistic solution to scene parsing by predicting instance labels and pixel-level classification. To improve the performance of our panoptic segmentation system, we explore various methods which will be described in later part of this report. We demonstrate in our report that the understanding of instance occlusion, the joint improvement by hybrid-task learning, and the study of panoptic segmentation metrics all play crucial roles. We also participated in Joint COCO and Mapillary Workshop at ICCV 2019. On test-dev dataset split, our ensemble model achieved PQ=53.5, ranked the 1st place (without external dataset) and the 2nd place (overall). |
| first_indexed | 2024-10-01T04:04:14Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/138017 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:04:14Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1380172020-04-22T02:44:24Z Towards high-quality panoptic segmentation Chen, Chongsong Chen Change Loy School of Computer Science and Engineering Sense International Pte. Ltd. ccloy@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Panoptic segmentation is a recently proposed task that unifies both instance and semantic segmentation. It provides a holistic solution to scene parsing by predicting instance labels and pixel-level classification. To improve the performance of our panoptic segmentation system, we explore various methods which will be described in later part of this report. We demonstrate in our report that the understanding of instance occlusion, the joint improvement by hybrid-task learning, and the study of panoptic segmentation metrics all play crucial roles. We also participated in Joint COCO and Mapillary Workshop at ICCV 2019. On test-dev dataset split, our ensemble model achieved PQ=53.5, ranked the 1st place (without external dataset) and the 2nd place (overall). Bachelor of Engineering (Computer Science) 2020-04-22T02:44:24Z 2020-04-22T02:44:24Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138017 en SCSE19-0115 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Chen, Chongsong Towards high-quality panoptic segmentation |
| title | Towards high-quality panoptic segmentation |
| title_full | Towards high-quality panoptic segmentation |
| title_fullStr | Towards high-quality panoptic segmentation |
| title_full_unstemmed | Towards high-quality panoptic segmentation |
| title_short | Towards high-quality panoptic segmentation |
| title_sort | towards high quality panoptic segmentation |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/138017 |
| work_keys_str_mv | AT chenchongsong towardshighqualitypanopticsegmentation |