Back to Search Start Over

Continual Learning in the Presence of Repetition

Authors :
Hemati, Hamed
Pellegrini, Lorenzo
Duan, Xiaotian
Zhao, Zixuan
Xia, Fangfang
Masana, Marc
Tscheschner, Benedikt
Veas, Eduardo
Zheng, Yuxiang
Zhao, Shiji
Li, Shao-Yuan
Huang, Sheng-Jun
Lomonaco, Vincenzo
van de Ven, Gido M.
Publication Year :
2024

Abstract

Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not often considered in standard benchmarks for CL. Unlike with the rehearsal mechanism in buffer-based strategies, where sample repetition is controlled by the strategy, repetition in the data stream naturally stems from the environment. This report provides a summary of the CLVision challenge at CVPR 2023, which focused on the topic of repetition in class-incremental learning. The report initially outlines the challenge objective and then describes three solutions proposed by finalist teams that aim to effectively exploit the repetition in the stream to learn continually. The experimental results from the challenge highlight the effectiveness of ensemble-based solutions that employ multiple versions of similar modules, each trained on different but overlapping subsets of classes. This report underscores the transformative potential of taking a different perspective in CL by employing repetition in the data stream to foster innovative strategy design.<br />Comment: Preprint; Challenge Report of the 4th Workshop on Continual Learning in Computer Vision at CVPR

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2405.04101
Document Type :
Working Paper