Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/138017
Title: Towards high-quality panoptic segmentation
Authors: Chen, Chongsong
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2020
Publisher: Nanyang Technological University
Project: SCSE19-0115
Abstract: 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).
URI: https://hdl.handle.net/10356/138017
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_CCS_amended.pdf
  Restricted Access
Amended Final Report (version1)6.09 MBAdobe PDFView/Open

Page view(s)

218
Updated on Dec 3, 2022

Download(s) 50

25
Updated on Dec 3, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.