The Library
Class similarity weighted knowledge distillation for continual semantic segmentation
Tools
Phan, Minh Hieu, Ta, The-Anh, Phung, Son Lam, Tran-Thanh, Long and Bouzerdoum, Abdesselam (2022) Class similarity weighted knowledge distillation for continual semantic segmentation. In: 2022 Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, USA, 19-24 Jun 2022 pp. 16866-16875.
|
PDF
WRAP-class-similarity-weighted-knowledge-distillation-continual-semantic-segmentation-Tran-Thanh-2022.pdf - Accepted Version - Requires a PDF viewer. Download (4090Kb) | Preview |
Official URL: https://openaccess.thecvf.com/content/CVPR2022/pap...
Abstract
Deep learning models are known to suffer from the problem of catastrophic forgetting when they incrementally learn new classes. Continual learning for semantic segmentation (CSS) is an emerging field in computer vision. We identify a problem in CSS: A model tends to be confused between old and new classes that are visually similar,
which makes it forget the old ones. To address this gap, we propose REMINDER - a new CSS framework and a novel class similarity knowledge distillation (CSW-KD) method. Our CSW-KD method distills the knowledge of a previous model on old classes that are similar to the new one. This provides two main benefits: (i) selectively revising old
classes that are more likely to be forgotten, and (ii) better learning new classes by relating them with the previously seen classes. Extensive experiments on Pascal-VOC 2012 and ADE20k datasets show that our approach outperforms state-of-the-art methods on standard CSS settings by up to 7.07% and 8.49%, respectively.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
Publisher: | IEEE | ||||||
Official Date: | 2022 | ||||||
Dates: |
|
||||||
Page Range: | pp. 16866-16875 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||
Date of first compliant deposit: | 5 April 2022 | ||||||
Date of first compliant Open Access: | 22 July 2022 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | 2022 Conference on Computer Vision and Pattern Recognition (CVPR 2022) | ||||||
Type of Event: | Conference | ||||||
Location of Event: | New Orleans, USA | ||||||
Date(s) of Event: | 19-24 Jun 2022 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year