An Efficient Replay for Class-Incremental Learning with Pre-trained Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Weimin, Xie, Bin Chen adn Chunzhao, Tan, Zhenhao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929460346880000
author Yin, Weimin
Xie, Bin Chen adn Chunzhao
Tan, Zhenhao
author_facet Yin, Weimin
Xie, Bin Chen adn Chunzhao
Tan, Zhenhao
contents In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental learning and Oracle training and have attempted to make corrections. In recent years, researchers have begun to develop class-incremental learning algorithms utilizing pre-trained models, achieving significant results. This paper observes that in class-incremental learning, the steady state among the weight guided by each class center is disrupted, which is significantly correlated with catastrophic forgetting. Based on this, we propose a new method to overcoming forgetting . In some cases, by retaining only a single sample unit of each class in memory for replay and applying simple gradient constraints, very good results can be achieved. Experimental results indicate that under the condition of pre-trained models, our method can achieve competitive performance with very low computational cost and by simply using the cross-entropy loss.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08084
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Efficient Replay for Class-Incremental Learning with Pre-trained Models
Yin, Weimin
Xie, Bin Chen adn Chunzhao
Tan, Zhenhao
Machine Learning
Artificial Intelligence
In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental learning and Oracle training and have attempted to make corrections. In recent years, researchers have begun to develop class-incremental learning algorithms utilizing pre-trained models, achieving significant results. This paper observes that in class-incremental learning, the steady state among the weight guided by each class center is disrupted, which is significantly correlated with catastrophic forgetting. Based on this, we propose a new method to overcoming forgetting . In some cases, by retaining only a single sample unit of each class in memory for replay and applying simple gradient constraints, very good results can be achieved. Experimental results indicate that under the condition of pre-trained models, our method can achieve competitive performance with very low computational cost and by simply using the cross-entropy loss.
title An Efficient Replay for Class-Incremental Learning with Pre-trained Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.08084