Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference

This paper focuses on the prevalent stage interference and stage performance imbalance of incremental learning. To avoid obvious stage learning bottlenecks, we propose a new incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task at each stage, without interference from others. To be concrete, to aggregate multiple stage classifiers as a uniform one impartially, we first introduce a temperature-controlled energy metric for indicating the confidence score levels of the stage classifiers. We then propose an anchor-based energy self-normalization strategy to ensure the stage classifiers work at the same energy level. Finally, we design a voting-based inference augmentation strategy for robust inference. The proposed method is rehearsal-free and can work for almost all incremental learning scenarios. We evaluate the proposed method on four large datasets. Extensive results demonstrate the superiority of the proposed method in setting up new state-of-the-art overall performance. Code is available at https://github.com/iamwangyabin/ESN.

Authors

• Yabin Wang Xi'an Jiaotong University Singapore Management University
• Zhiheng Ma Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Computility Microelectronics Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
• Zhiwu Huang Singapore Management University University of Southampton
• Yaowei Wang Pengcheng Laboratory Harbin Institute of Technology, Shenzhen
• Zhou Su Xi'an Jiaotong University
• Xiaopeng Hong Harbin Institute of Technology Pengcheng Laboratory

Keywords

• CV: Representation Learning for Vision
• ML: Classification and Regression
• ML: Lifelong and Continual Learning
• ML: Transfer, Domain Adaptation, Multi-Task Learning