Few-shot Class-incremental Learning: A Survey
- URL: http://arxiv.org/abs/2308.06764v2
- Date: Sat, 16 Dec 2023 23:13:26 GMT
- Title: Few-shot Class-incremental Learning: A Survey
- Authors: Jinghua Zhang and Li Liu and Olli Silv\'en and Matti Pietik\"ainen and
Dewen Hu
- Abstract summary: Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML)
This paper aims to provide a comprehensive and systematic review of FSCIL.
- Score: 16.729567512584822
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning [52.63674911541416]
Few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and forgetting.
Our primary focus is representation learning on base classes to tackle the unique challenge of FSCIL.
We find that trying to secure the spread of features within a more confined feature space enables the learned representation to strike a better balance between transferability and discriminability.
arXiv Detail & Related papers (2024-10-08T02:23:16Z) - Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospects [84.36935309169567]
We present a broad review of recent advances for fine-grained analysis in zero-shot learning (ZSL)
We first provide a taxonomy of existing methods and techniques with a thorough analysis of each category.
Then, we summarize the benchmark, covering publicly available datasets, models, implementations, and some more details as a library.
arXiv Detail & Related papers (2024-01-31T11:51:24Z) - Low-shot Object Learning with Mutual Exclusivity Bias [27.67152913041082]
This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias.
We provide a novel dataset, comprehensive baselines, and a state-of-the-art method to enable the ML community to tackle this challenging learning task.
arXiv Detail & Related papers (2023-12-06T14:54:10Z) - S3C: Self-Supervised Stochastic Classifiers for Few-Shot
Class-Incremental Learning [22.243176199188238]
Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes.
FSCIL suffers from two major challenges: (i) over-fitting on the new classes due to limited amount of data, (ii) catastrophically forgetting about the old classes due to unavailability of data from these classes in the incremental stages.
arXiv Detail & Related papers (2023-07-05T12:41:46Z) - A Survey on Few-Shot Class-Incremental Learning [11.68962265057818]
Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks.
This paper provides a comprehensive survey on FSCIL.
FSCIL has achieved impressive achievements in various fields of computer vision.
arXiv Detail & Related papers (2023-04-17T10:15:08Z) - Uncertainty Estimation by Fisher Information-based Evidential Deep
Learning [61.94125052118442]
Uncertainty estimation is a key factor that makes deep learning reliable in practical applications.
We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL)
In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
arXiv Detail & Related papers (2023-03-03T16:12:59Z) - Mitigating Forgetting in Online Continual Learning via Contrasting
Semantically Distinct Augmentations [22.289830907729705]
Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one.
Main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
arXiv Detail & Related papers (2022-11-10T05:29:43Z) - Recent Few-Shot Object Detection Algorithms: A Survey with Performance
Comparison [54.357707168883024]
Few-Shot Object Detection (FSOD) mimics the humans' ability of learning to learn.
FSOD intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes.
We give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols.
arXiv Detail & Related papers (2022-03-27T04:11:28Z) - Learning with Multiclass AUC: Theory and Algorithms [141.63211412386283]
Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems.
In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics.
arXiv Detail & Related papers (2021-07-28T05:18:10Z) - Few-Shot Class-Incremental Learning [68.75462849428196]
We focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem.
FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones.
We represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes.
arXiv Detail & Related papers (2020-04-23T03:38:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.