YCYi-Qun Chen
Yi-Qun Chen
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yi-Qun Chen has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Gang Zhang
School of Automation, Guangdong University of Technology, Guangzhou 510006, China
1 shared publication - Haolin Pan
South China University of Technology, China
1 shared publication Haomin Yang
South China University of Technology, China
1 shared publication- Hong-Tao Liu
School of Automation, Guangdong University of Technology, Guangzhou 510006, China
1 shared publication - Jian Chen
South China University of Technology
1 shared publication - Qinyi Deng
South China University of Technology, China
1 shared publication
Latest Publications
- Open Access
- 10 June 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (12) , 7009
A Histopathological Image Classification Method Based on Model Fusion in the Weight Space
Automatic classification of histopathological images plays an important role in computer-aided diagnosis systems. The automatic classification model of histopathological images based on deep neural networks has received widespread attention. However, the performance of deep models is affected by many factors, such as training hyperparameters, model structure, dataset quality, and training cost. In order to reduce the impact of the above factors on model training and reduce the training and inference costs of the model, we propose a novel method based on model fusion in the weight space, which is inspired by stochastic weight averaging and model soup. We use the cyclical learning rate (CLR) strategy to fine-tune the ingredient models and propose a ranking strategy based on accuracy and diversity for candidate model selection. Compared to the single model, the weight fusion of ingredient models can obtain a model whose performance is closer to the expected value of the error basin, which may improve the generalization ability of the model. Compared to the ensemble model with n base models, the testing cost of the proposed model is theoretically of that of the ensemble model. Experimental results on two histopathological image datasets show the effectiveness of the proposed model in comparison to baseline ones, including ResNet, VGG, DenseNet, and their ensemble versions.- 10 June 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (12) , 7009
Open AccessA Histopathological Image Classification Method Based on Model Fusion in the Weight Space
Automatic classification of histopathological images plays an important role in computer-aided diagnosis systems. The automatic classification model of histopathological images based on deep neural networks has received widespread attention. However, the performance of deep models is affected by many factors, such as training hyperparameters, model structure, dataset quality, and training cost. In order to reduce the impact of the above factors on model training and reduce the training and inference costs of the model, we propose a novel method based on model fusion in the weight space, which is inspired by stochastic weight averaging and model soup. We use the cyclical learning rate (CLR) strategy to fine-tune the ingredient models and propose a ranking strategy based on accuracy and diversity for candidate model selection. Compared to the single model, the weight fusion of ingredient models can obtain a model whose performance is closer to the expected value of the error basin, which may improve the generalization ability of the model. Compared to the ensemble model with n base models, the testing cost of the proposed model is theoretically of that of the ensemble model. Experimental results on two histopathological image datasets show the effectiveness of the proposed model in comparison to baseline ones, including ResNet, VGG, DenseNet, and their ensemble versions. - 23 December 2022
- Published by Elsevier in Neural Networks
- Vol. 159, 198-207
Improving fine-tuning of self-supervised models with Contrastive Initialization
- 23 December 2022
- Published by Elsevier in Neural Networks
- Vol. 159, 198-207
Improving fine-tuning of self-supervised models with Contrastive Initialization