Guanghao Jin¹, Chunmei Pei¹, Na Zhao¹, Hengguang Li², Qingzeng Song³, Jing Yu^1,*

CMC-Computers, Materials & Continua, Vol.73, No.3, pp. 5185-5196, 2022, DOI:10.32604/cmc.2022.027307

Abstract When utilizing the deep learning models in some real applications, the distribution of the labels in the environment can be used to increase the accuracy. Generally, to compute this distribution, there should be the validation set that is labeled by the ground truths. On the other side, the dependency of ground truths limits the utilization of the distribution in various environments. In this paper, we carried out a novel system for the deep learning-based classification to solve this problem. Firstly, our system only uses one validation set with ground truths to compute some hyper parameters, which is named as one-shot… More >

Guanghao Jin¹, Na Zhao¹, Chunmei Pei¹, Hengguang Li², Qingzeng Song³, Jing Yu^1,*

Journal on Artificial Intelligence, Vol.3, No.4, pp. 135-143, 2021, DOI:10.32604/jai.2021.027154

Abstract Generally, the performance of deep learning models is related to the captured features of training samples. When the training samples belong to different domains, the diverse features may increase the difficulty of training high performance models. In this paper, we built a new framework that generates multiple models on the organized samples to increase the accuracy of classification. Firstly, our framework selects some existing models and trains each of them on organized training sets to get multiple trained models. Secondly, we select some of them based on a validation set. Finally, we use some fusion method on the outputs of… More >