Please use this identifier to cite or link to this item:
Title: Continual semantic segmentation via image and latent space consistency
Authors: Wang, Zhichao
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Wang, Z. (2021). Continual semantic segmentation via image and latent space consistency. Master's thesis, Nanyang Technological University, Singapore.
Abstract: In this thesis, my continual-learning research process is introduced in detail, including a novel method and two regulators, which contribute to anti-forgetting Result in continual learning in the semantic segmentation area. Firstly a real-time semantic segmentation model called ERFnet is evaluated, then based on this network and Cityscapes dataset, a model-recall method is proposed which could significantly reduce the catastrophic forgetting which happens in the process of continual learning in the semantic segmentation area; inspired by mentors, 2 regulators are also conducted which were expected to further improve performance (one regulator is come up by mentors and another is by myself). A couple of experiments are designed to evaluate the performance of the new Idea and prediction images for each step is visible.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Wang Zhichao_Dissertation.pdf
  Restricted Access
3.95 MBAdobe PDFView/Open

Page view(s)

Updated on Jan 20, 2022


Updated on Jan 20, 2022

Google ScholarTM


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