Few-shot Class-incremental Learning for Classification and Object Detection: A Survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jinghua, Liu, Li, Silvén, Olli, Pietikäinen, Matti, Hu, Dewen
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915095233167360
author Zhang, Jinghua
Liu, Li
Silvén, Olli
Pietikäinen, Matti
Hu, Dewen
author_facet Zhang, Jinghua
Liu, Li
Silvén, Olli
Pietikäinen, Matti
Hu, Dewen
contents Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, it remains an active exploration area. This paper aims to provide a comprehensive and systematic review of FSCIL. In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL). Besides, we offer an overview of benchmark datasets and evaluation metrics. Furthermore, we introduce the Few-shot Class-incremental Classification (FSCIC) methods from data-based, structure-based, and optimization-based approaches and the Few-shot Class-incremental Object Detection (FSCIOD) methods from anchor-free and anchor-based approaches. Beyond these, we present several promising research directions within FSCIL that merit further investigation.
format Preprint
id arxiv_https___arxiv_org_abs_2308_06764
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Few-shot Class-incremental Learning for Classification and Object Detection: A Survey
Zhang, Jinghua
Liu, Li
Silvén, Olli
Pietikäinen, Matti
Hu, Dewen
Machine Learning
Artificial Intelligence
Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, it remains an active exploration area. This paper aims to provide a comprehensive and systematic review of FSCIL. In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL). Besides, we offer an overview of benchmark datasets and evaluation metrics. Furthermore, we introduce the Few-shot Class-incremental Classification (FSCIC) methods from data-based, structure-based, and optimization-based approaches and the Few-shot Class-incremental Object Detection (FSCIOD) methods from anchor-free and anchor-based approaches. Beyond these, we present several promising research directions within FSCIL that merit further investigation.
title Few-shot Class-incremental Learning for Classification and Object Detection: A Survey
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2308.06764