Continual semantic segmentation via image and latent space consistency
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 evaluat...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/154665 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | 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. |
|---|