Joint Input and Output Coordination for Class-Incremental Learning

Shuai Wang, Yibing Zhan, Yong Luo*, Han Hu, Wei Yu*, Yonggang Wen, Dacheng Tao

*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, current strategies still do not 1) adequately address the class bias problem, and 2) alleviate the mutual interference between new and old tasks, and 3) consider the problem of class bias within tasks. This motivates us to propose a joint input and output coordination (JIOC) mechanism to address these issues. This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks. The proposed mechanism is general and flexible, and can be incorporated into different incremental learning approaches that use memory storage. Extensive experiments show that our mechanism can significantly improve their performance.

Original languageEnglish
Title of host publicationProceedings of the 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
EditorsKate Larson
PublisherInternational Joint Conferences on Artificial Intelligence
Pages5108-5116
Number of pages9
ISBN (Electronic)9781956792041
Publication statusPublished - 2024
Event33rd International Joint Conference on Artificial Intelligence, IJCAI 2024 - Jeju, Korea, Republic of
Duration: 3 Aug 20249 Aug 2024

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
Country/TerritoryKorea, Republic of
CityJeju
Period3/08/249/08/24

Fingerprint

Dive into the research topics of 'Joint Input and Output Coordination for Class-Incremental Learning'. Together they form a unique fingerprint.

Cite this