Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification
Applied Computing and Intelligence · 2023
DOI: 10.3934/aci.2023002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Computing and Intelligence, 2023. Verfasst von Hao Zhen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben.
Abstract (Originalsprache)
Classification using supervised learning requires annotating a large amount of classes-balanced data for model training and testing. This has practically limited the scope of applications with supervised learning, in particular deep learning. To address the issues associated with limited and imbalanced data, this paper introduces a sample-efficient co-supervised learning paradigm (SEC-CGAN), in which a conditional generative adversarial network (CGAN) is trained alongside the classifier and supplements semantics-conditioned, confidence-aware synthesized examples to the annotated data during the training process. In this setting, the CGAN not only serves as a co-supervisor but also provides complementary quality examples to aid the classifier training in an end-to-end fashion. Experiments demonstrate that the proposed SEC-CGAN outperforms the external classifier GAN (EC-GAN) and a baseline ResNet-18 classifier. For the comparison, all classifiers in above methods adopt the ResNet-18 architecture as the backbone. Particularly, for the Street View House Numbers dataset, using the 5% of training data, a test accuracy of 90.26% is achieved by SEC-CGAN as opposed to 88.59% by EC-GAN and 87.17% by the baseline classifier; for the highway image dataset, using the 10% of training data, a test accuracy of 98.27% is achieved by SEC-CGAN, compared to 97.84% by EC-GAN and 95.52% by the baseline classifier.
Zitieren
APA
Zhen, H., Shi, Y., Yang, J. J., & Vehni, J. M. (2023). Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification. Applied Computing and Intelligence. https://doi.org/10.3934/aci.2023002
Vancouver
Zhen H, Shi Y, Yang JJ, Vehni JM. Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification. Applied Computing and Intelligence. 2023. doi:10.3934/aci.2023002
BibTeX
@article{Zhen2023,
author = {Zhen, Hao and Shi, Yucheng and Yang, Jidong J. and Vehni, Javad Mohammadpour},
title = {Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification},
journal = {Applied Computing and Intelligence},
year = {2023},
doi = {10.3934/aci.2023002}
}
EUVIMED