Tri-Branch GAN: A Semi-supervised Method Based on Rebalance
- 27 September 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 33, 171-176
Abstract
For deep learning applications in industrial scenarios, few-shot and imbalanced available datasets are very common. Traditional methods usually adopt the idea of hierarchical training, semi-supervised learning and the rebalancing method to train the model respectively, which has certain limitations: Separate trainings does not fully exploit the correlation between the two problems and causes additional computational overhead. Therefore, this paper proposes a semi-supervised learning method based on rebalance, named as Tri-branch GAN (Generative Adversarial Networks). This method makes full use of the correlation between the two problems, avoids the updating coating problem after the model parameter training, and saves the computational cost. Simulation results show that the proposed method can effectively improve the classification accuracy.Keywords
This publication has 7 references indexed in Scilit:
- Prenatal prediction of neonatal respiratory morbidity: a radiomics method based on imbalanced few-shot fetal lung ultrasound imagesBMC Medical Imaging, 2022
- Improving Calibration for Long-Tailed Recognition2021
- A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training DataComputational Intelligence and Neuroscience, 2021
- Mitigating long tail effect in recommendations using few shot learning techniqueExpert Systems with Applications, 2020
- Cumulative Learning2019
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Focal Loss for Dense Object Detection2017