Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

1-2024

Abstract

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction inconsistencies between old and new models. Such prediction is made with almost new class data, as old class data is extremely scarce due to the strict memory limitation in CIL. In this paper, we take a deep dive into KD losses and find that "using new class data for KD"not only hinders the model adaption (for learning new classes) but also results in low efficiency for preserving old class knowledge. We address this by "using the placebos of old classes for KD", where the placebos are chosen from a free image stream, such as Google Images, in an automatical and economical fashion. To this end, we train an online placebo selection policy to quickly evaluate the quality of streaming images (good or bad placebos) and use only good ones for one-time feed-forward computation of KD. We formulate the policy training process as an online Markov Decision Process (MDP), and introduce an online learning algorithm to solve this MDP problem without causing much computation costs. In experiments, we show that our method 1) is surprisingly effective even when there is no class overlap between placebos and original old class data, 2) does not require any additional supervision or memory budget, and 3) significantly outperforms a number of top-performing CIL methods, in particular when using lower memory budgets for old class exemplars, e.g., five exemplars per class. https://github.com/yaoyao-liu/online-placebos

Keywords

And algorithm, Data class, Deep dives, Formulation, Incremental learning, Learning architectures, Machine learning architecture, Machine-learning, Markov Decision Processes, Model adaption

Discipline

Databases and Information Systems | Theory and Algorithms

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Publication

Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, United States of America, January 4-8

First Page

2215

Last Page

2224

ISBN

9798350318920

Identifier

10.1109/WACV57701.2024.00222

Publisher

IEEE

City or Country

New Jersey

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/WACV57701.2024.00222

Download

Share

COinS