CoChat
Sign Up
Cited by 44Domain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsMachine Learning and Data Classification

Uncertainty-Guided Semi-Supervised Few-Shot Class-Incremental Learning With Knowledge Distillation

Cui, Yawen, Deng, Wanxia, Xu, Xin, Liu, Zhen, Liu, Zhong, Pietikäinen, Matti, Liu, Li·2023·IEEE Transactions on Multimedia
DOI 10.1109/tmm.2022.3208743
Open this paper in CoChat — free account

Abstract

Class-Incremental Learning (CIL) aims at incrementally learning novel classes without forgetting old ones. This capability becomes more challenging when novel tasks contain one or a few labeled training samples, which leads to a more practical learning scenario,i.e., Few-Shot Class- Incremental Learning (FSCIL). The dilemma on FSCIL lies in serious overfitting and exacerbated catastrophic forgetting caused by the limited training data from novel classes. In this paper, excited by the easy accessibility of unlabeled data, we conduct a pioneering work and focus on a Semi-Supervised Few-Shot Class-Incremental Learning (Semi-FSCIL) problem, which requires the model incrementally to learn new classes from extremely limited labeled samples and a large number of unlabeled samples. To address this problem, a simple but efficient framework is first constructed based on the knowledge distillation technique to alleviate catastrophic forgetting. To efficiently mitigate the overfitting problem on novel categories with unlabeled data, uncertainty-guided semi-supervised learning is incorporated into this framework to select unlabeled samples into incremental learning sessions considering the model uncertainty. This process provides extra reliable supervision for the distillation process and contributes to better formulating the class means. Our extensive experiments on CIFAR100, miniImageNet and CUB200 datasets demonstrate the promising performance of our proposed method, and define baselin…

Integrity signals

Registry

Crossref · 10.1109/tmm.2022.3208743

Cites

11 of 11 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Some studies use knowledge distillation to maintain competent classification capabilities on previous classes while learning new ones.

    “To mitigate catastrophic forgetting, some studies [44, 45, 46] use KD to maintain competent classification capabilities on previous classes while learning new ones.”

    From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [45]

  • Cui et al. [45] introduced the Us-KD framework, which used an uncertainty-guided module to select unlabeled data to mitigate overfitting during knowledge transfer.

    “Cui et al. [45] introduced the Us-KD framework, which used an uncertainty-guided module to select unlabeled data to mitigate overfitting during knowledge transfer.”

    From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [45]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Cui, Y., Deng, W., Xu, X., Liu, Z., Liu, Z., Pietikäinen, M., & Liu, L.
Affiliations
  • University of Oulu (FI)
  • National University of Defense Technology (CN)
ORCID
Venue
IEEE Transactions on Multimedia
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2023
Volume
25
Pages
6422-6435
ISSN
  • 1520-9210 (ISSN-L)
  • 1941-0077
DOI
10.1109/tmm.2022.3208743
OpenAlex
W4296916378
Cited by
44
References
11
Citations by year
2026: 6 · 2025: 19 · 2024: 13 · 2023: 6
FWCI
3.13
Type
journal article
Language
en
Open access
closed
Licence
Locations
IEEE Transactions on Multimedia (publishedVersion)
Funders
  • National Key Research and Development Program of China (2021YFB3100800)
  • Academy of Finland (331883)
  • National Natural Science Foundation of China (61872379, 62022091)
  • China Scholarship Council (201903170129)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
Keywords
class-incremental learning, few-shot learning, semi-supervised learning, catastrophic forgetting, knowledge distillation, unlabeled data, overfitting, sample selection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review