Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Da-Wei, Sun, Hai-Long, Ye, Han-Jia, Zhan, De-Chuan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914718792286208
author Zhou, Da-Wei
Sun, Hai-Long
Ye, Han-Jia
Zhan, De-Chuan
author_facet Zhou, Da-Wei
Sun, Hai-Long
Ye, Han-Jia
Zhan, De-Chuan
contents Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often results in the overwriting of old ones. Excessive modification of the network causes forgetting, while minimal adjustments lead to an inadequate fit for new classes. As a result, it is desired to figure out a way of efficient model updating without harming former knowledge. In this paper, we propose ExpAndable Subspace Ensemble (EASE) for PTM-based CIL. To enable model updating without conflict, we train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. These adapters span a high-dimensional feature space, enabling joint decision-making across multiple subspaces. As data evolves, the expanding subspaces render the old class classifiers incompatible with new-stage spaces. Correspondingly, we design a semantic-guided prototype complement strategy that synthesizes old classes' new features without using any old class instance. Extensive experiments on seven benchmark datasets verify EASE's state-of-the-art performance. Code is available at: https://github.com/sun-hailong/CVPR24-Ease
format Preprint
id arxiv_https___arxiv_org_abs_2403_12030
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
Zhou, Da-Wei
Sun, Hai-Long
Ye, Han-Jia
Zhan, De-Chuan
Computer Vision and Pattern Recognition
Machine Learning
Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often results in the overwriting of old ones. Excessive modification of the network causes forgetting, while minimal adjustments lead to an inadequate fit for new classes. As a result, it is desired to figure out a way of efficient model updating without harming former knowledge. In this paper, we propose ExpAndable Subspace Ensemble (EASE) for PTM-based CIL. To enable model updating without conflict, we train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. These adapters span a high-dimensional feature space, enabling joint decision-making across multiple subspaces. As data evolves, the expanding subspaces render the old class classifiers incompatible with new-stage spaces. Correspondingly, we design a semantic-guided prototype complement strategy that synthesizes old classes' new features without using any old class instance. Extensive experiments on seven benchmark datasets verify EASE's state-of-the-art performance. Code is available at: https://github.com/sun-hailong/CVPR24-Ease
title Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.12030