Semi-supervised few-shot class-incremental learning
Cui, Yawen; Xiong, Wuti; Tavakolian, Mohammad; Liu, Li (2021-08-23)
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.
© 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.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe2023040334602
Tiivistelmä
Abstract
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.
Kokoelmat
- Avoin saatavuus [38618]