Saved in:
Bibliographic Details
Main Authors: Tang, Yu-Ming, Peng, Yi-Xing, Meng, Jingke, Zheng, Wei-Shi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.07468
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917717828698112
author Tang, Yu-Ming
Peng, Yi-Xing
Meng, Jingke
Zheng, Wei-Shi
author_facet Tang, Yu-Ming
Peng, Yi-Xing
Meng, Jingke
Zheng, Wei-Shi
contents Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited samples in a few-shot fashion. Inherited from the classical class-incremental learning setting, the popular benchmark of FSCIL uses averaged accuracy (aAcc) and last-task averaged accuracy (lAcc) as the evaluation metrics. However, we reveal that such evaluation metrics may not provide adequate emphasis on the novel class performance, and the continual learning ability of FSCIL methods could be ignored under this benchmark. In this work, as a complement to existing metrics, we offer a new metric called generalized average accuracy (gAcc) which is designed to provide an extra equitable evaluation by incorporating different perspectives of the performance under the guidance of a parameter $α$. We also present an overall metric in the form of the area under the curve (AUC) along the $α$. Under the guidance of gAcc, we release the potential of intermediate features of the vision transformers to boost the novel-class performance. Taking information from intermediate layers which are less class-specific and more generalizable, we manage to rectify the final features, leading to a more generalizable transformer-based FSCIL framework. Without complex network designs or cumbersome training procedures, our method outperforms existing FSCIL methods at aAcc and gAcc on three datasets. See codes at https://github.com/iSEE-Laboratory/Revisting_FSCIL
format Preprint
id arxiv_https___arxiv_org_abs_2407_07468
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rethinking Few-shot Class-incremental Learning: Learning from Yourself
Tang, Yu-Ming
Peng, Yi-Xing
Meng, Jingke
Zheng, Wei-Shi
Computer Vision and Pattern Recognition
Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited samples in a few-shot fashion. Inherited from the classical class-incremental learning setting, the popular benchmark of FSCIL uses averaged accuracy (aAcc) and last-task averaged accuracy (lAcc) as the evaluation metrics. However, we reveal that such evaluation metrics may not provide adequate emphasis on the novel class performance, and the continual learning ability of FSCIL methods could be ignored under this benchmark. In this work, as a complement to existing metrics, we offer a new metric called generalized average accuracy (gAcc) which is designed to provide an extra equitable evaluation by incorporating different perspectives of the performance under the guidance of a parameter $α$. We also present an overall metric in the form of the area under the curve (AUC) along the $α$. Under the guidance of gAcc, we release the potential of intermediate features of the vision transformers to boost the novel-class performance. Taking information from intermediate layers which are less class-specific and more generalizable, we manage to rectify the final features, leading to a more generalizable transformer-based FSCIL framework. Without complex network designs or cumbersome training procedures, our method outperforms existing FSCIL methods at aAcc and gAcc on three datasets. See codes at https://github.com/iSEE-Laboratory/Revisting_FSCIL
title Rethinking Few-shot Class-incremental Learning: Learning from Yourself
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.07468