Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation

Minh Hieu Phan, The Anh Ta, Son Lam Phung, Long Tran-Thanh, Abdesselam Bouzerdoum

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

35 Citations (Scopus)

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.

Original languageEnglish
Title of host publication2022 Ieee/cvf Conference On Computer Vision And Pattern Recognition (cvpr 2022)
PublisherIEEE Computer Society
Pages16845-16854
Number of pages10
ISBN (Electronic)9781665469463
DOIs
Publication statusPublished - 2022
Event2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States
Duration: 19 Jun 202224 Jun 2022

Publication series

NameIeee Conference On Computer Vision And Pattern Recognition

Conference

Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Country/TerritoryUnited States
CityNew Orleans
Period19/06/2224/06/22

Keywords

  • Computer vision theory
  • Deep learning architectures and techniques
  • Efficient learning and inferences
  • Representation learning
  • Scene analysis and understanding
  • Segmentation
  • Vision applications and systems
  • grouping and shape analysis

Fingerprint

Dive into the research topics of 'Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation'. Together they form a unique fingerprint.

Cite this