University of Oulu

Y. Cui, W. Xiong, M. Tavakolian and L. Liu, "Semi-Supervised Few-Shot Class-Incremental Learning," 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA, 2021, pp. 1239-1243, doi: 10.1109/ICIP42928.2021.9506346.

Semi-supervised few-shot class-incremental learning

Saved in:
Author: Cui, Yawen1; Xiong, Wuti1; Tavakolian, Mohammad1;
Organizations: 1Univeristy of Oulu, Finland
2National University of Defense Technology, China
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.5 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2023-04-03


The capability of incrementally learning new classes and learning from a few examples is one of the hallmarks of human intelligence. It is crucial to endow a practical recognition system with such ability. Therefore, in this paper, we conduct pioneering work and focus on a challenging yet practical Semi-Supervised Few-Shot Class-Incremental Learning (SSFSCIL) problem, which requires CNN models incrementally learn new classes from very few labeled samples and a large number of unlabeled samples, without forgetting the previously learned ones. To address this problem, a simple and efficient solution for SSFSCIL is proposed to learn novel categories using a self-training strategy in a semi-supervised manner and avoid catastrophic forgetting by distillation-based methods. Our extensive experiments on CIFAR100, mini ImageNet and CUB200 datasets demonstrate the promising performance of our proposed method, and define baselines in this new research direction.

see all

Series: IEEE International Conference on Image Processing
ISSN: 1522-4880
ISSN-E: 2381-8549
ISSN-L: 1522-4880
ISBN: 978-1-6654-4115-5
ISBN Print: 978-1-6654-3102-6
Article number: 9506346
DOI: 10.1109/icip42928.2021.9506346
Host publication: 2021 IEEE International Conference on Image Processing (ICIP)
Conference: IEEE International Conference on Image Processing
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.