Mnemonics Training: Multi-Class Incremental Learning without Forgetting

Yaoyao Liu¹   Yuting Su²   An-An Liu²   Bernt Schiele¹   Qianru Sun³

¹Max Planck Institute for Informatics   ²Tianjin University   ³Singapore Management University  

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (Oral)

Abstract

Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones. To alleviate this issue, it has been proposed to keep around a few examples of the previous concepts but the effectiveness of this approach heavily depends on the representativeness of these examples. This paper proposes a novel and automatic framework we call mnemonics, where we parameterize exemplars and make them optimizable in an end-to-end manner. We train the framework through bilevel optimizations, i.e., model-level and exemplar-level. We conduct extensive experiments on three MCIL benchmarks, CIFAR-100, ImageNet-Subset and ImageNet, and show that using mnemonics exemplars can surpass the state-of-the-art by a large margin. Interestingly and quite intriguingly, the mnemonics exemplars tend to be on the boundaries between classes.

Contributions

• A novel mnemonics training framework that alternates the learning of exemplars and models in a global bilevel optimization program.
• A novel local bilevel optimization program that trains exemplars for new classes as well as adjusts exemplars of old classes in an end-to-end manner.
• In-depth experiments, visualization and explanation of mnemonics exemplars in the feature space.

Oral Talk (subtitles available)

Pipeline

The computing flow of the proposed mnemonics training. It is a global BOP that alternates the learning of mnemonics exemplars (we call exemplar-level optimization) and MCIL models (model-level optimization).

Performance

t-SNE Visualization

Citation

Please cite our paper if it is helpful to your work:

@inproceedings{liu2020mnemonics,
author    = {Liu, Yaoyao and Su, Yuting and Liu, An{-}An and Schiele, Bernt and Sun, Qianru},
title     = {Mnemonics Training: Multi-Class Incremental Learning without Forgetting},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages     = {12245--12254},
year      = {2020}
}

Contact

Copyright © 2020-2021 Max Planck Institute for Informatics | Imprint / Impressum | Data Protection / Datenschutzhinweis