Abstract
Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task boundary; where tasks shares classes and is more realistic and practical. To address such task, we argue the importance of diversity of samples in an episodic memory. To enhance the sample diversity in the memory, we propose a novel memory management strategy based on per-sample classification uncertainty and data augmentation, named Rainbow Memory (RM). With extensive empirical validations on MNIST, CIFAR10, CIFAR100, and ImageNet datasets, we show that the proposed method significantly improves the accuracy in blurry continual learning setups, outperforming state of the arts by large margins despite its simplicity. Code and data splits will be available in https://github.com/clovaai/rainbow-memory.
Original language | English |
---|---|
Title of host publication | Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 |
Publisher | IEEE Computer Society |
Pages | 8214-8223 |
Number of pages | 10 |
ISBN (Electronic) | 9781665445092 |
DOIs | |
Publication status | Published - 2021 |
Event | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States Duration: 2021 Jun 19 → 2021 Jun 25 |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
ISSN (Print) | 1063-6919 |
Conference
Conference | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 21/6/19 → 21/6/25 |
Bibliographical note
Funding Information:JC is partly supported by the National Research Foundation of Korea (NRF) (No.2019R1C1C1009283) and Institute of Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019-0-01842, Artificial Intelligence Graduate School Program (GIST) and No.2019-0-01351, Development of Ultra Low-Power Mobile Deep Learning Semiconductor With Compression/Decompression of Activation/Kernel Data), and Center for Applied Research in Artificial Intelligence (CARAI) grant funded by Defense Acquisition Program Administration (DAPA) and Agency for Defense Development (ADD) (UD190031RD). All authors thank Sung-min Cha (NAVER AI Lab) and Hyeonseo Koh (GIST) for discussions, and NAVER Smart Machine Learning (NSML) [25] team for GPU support.
Funding Information:
Acknowledgement. JC is partly supported by the National Research Foundation of Korea (NRF) (No.2019R1C1C1009283) and Institute of Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019-0-01842, Artificial Intelligence Graduate School Program (GIST) and No.2019-0-01351, Development of Ultra Low-Power Mobile Deep Learning Semiconductor With Compression/Decompression of Activation/Kernel Data), and Center for Applied Research in Artificial Intelligence (CARAI) grant funded by Defense Acquisition Program Administration (DAPA) and Agency for Defense Development (ADD) (UD190031RD). All authors thank Sung-min Cha (NAVER AI Lab) and Hyeonseo Koh (GIST) for discussions, and NAVER Smart Machine Learning (NSML) [25] team for GPU support.
Publisher Copyright:
© 2021 IEEE
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition