Memory Efficient Class-Incremental Learning for Image Classification

Abstract

With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples rather than the original real high-fidelity exemplar samples. Such a memory-efficient exemplar preserving scheme makes the old-class knowledge transfer more effective. However, the low-fidelity exemplar samples are often distributed in a different domain away from that of the original exemplar samples, that is, a domain shift. To alleviate this problem, we propose a duplet learning scheme that seeks to construct domain-compatible feature extractors and classifiers, which greatly narrows down the above domain gap. As a result, these low-fidelity auxiliary exemplar samples have the ability to moderately replace the original exemplar samples with a lower memory cost. In addition, we present a robust classifier adaptation scheme, which further refines the biased classifier (learned with the samples containing distillation label knowledge about old classes) with the help of the samples of pure true class labels. Experimental results demonstrate the effectiveness of this work against the state-of-the-art approaches.

References in corpus (15)

• Overcoming catastrophic forgetting in neural networks
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Continual Learning Through Synaptic Intelligence
• Efficient Lifelong Learning with A-GEM
• Maximum Density Divergence for Domain Adaptation
• FearNet: Brain-Inspired Model for Incremental Learning
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• Reinforced Continual Learning
• Generative replay with feedback connections as a general strategy for continual learning
• Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
• Incremental Classifier Learning with Generative Adversarial Networks
• A comprehensive, application-oriented study of catastrophic forgetting in DNNs
• Continual Classification Learning Using Generative Models
• Neural Architecture Search for Class-incremental Learning