DeepAI AI Chat
Log In Sign Up

Memory Efficient Class-Incremental Learning for Image Classification

by   Hanbin Zhao, et al.
Zhejiang University

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 memory-efficient exemplar preserving scheme make 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. We will release the code, baselines, and training statistics for all models to facilitate future research.


page 1

page 3

page 4


Class-incremental Learning via Deep Model Consolidation

Deep neural networks (DNNs) often suffer from "catastrophic forgetting" ...

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Class-incremental semantic segmentation (CISS) labels each pixel of an i...

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

Real-world applications require the classification model to adapt to new...

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

Non-exemplar class-incremental learning is to recognize both the old and...

Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning

Few-shot class-incremental learning(FSCIL) focuses on designing learning...

Constrained Few-shot Class-incremental Learning

Continually learning new classes from fresh data without forgetting prev...

Memory-Efficient Incremental Learning Through Feature Adaptation

In this work we introduce an approach for incremental learning, which pr...