Memory Efficient Class-Incremental Learning for Image Classification

doi:10.1109/TNNLS.2021.3072041

2022-10-01

DOI：10.1109/TNNLS.2021.3072041

原文链接

查看原文

摘要

En 中文

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. We will release the code, baselines, and training statistics for all models to facilitate future research.

Keyword:

Feature extraction

Knowledge transfer

Data mining

Adaptation models

Training

Noise measurement

Knowledge engineering

Catastrophic forgetting

class-incremental learning (CIL)

classification

exemplar