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 valid...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 guidance.Secondly,in an environment,our system builds the validation set and labels this by the prediction results,which does not need any guidance by the ground truths.Thirdly,the computed distribution of labels by the validation set selectively cooperates with the probability of labels by the output of models,which is to increase the accuracy of predict results on testing samples.We selected six popular deep learning models on three real datasets for the evaluation.The experimental results show that our system can achieve higher accuracy than state-of-art methods while reducing the dependency of labeled validation set.展开更多
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 train...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 the selected models to get more accurate results.The experimental results show that our framework achieved higher accuracy than the existing methods.Our framework can be an option for the deep learning system to increase the classification accuracy.展开更多
基金NationalNatural Science Foundation of China(GrantNos.61802279,6180021345,61702281,and 61702366)Natural Science Foundation of Tianjin(Grant Nos.18JCQNJC70300,19JCTPJC49200,19PTZWHZ00020,and 19JCYBJC15800)+2 种基金Fundamental Research Funds for the Tianjin Universities(Grant No.2019KJ019)the Tianjin Science and Technology Program(Grant No.19PTZWHZ00020)and in part by the State Key Laboratory of ASIC and System(Grant No.2021KF014)Tianjin Educational Commission Scientific Research Program Project(Grant Nos.2020KJ112 and 2018KJ215).
文摘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 guidance.Secondly,in an environment,our system builds the validation set and labels this by the prediction results,which does not need any guidance by the ground truths.Thirdly,the computed distribution of labels by the validation set selectively cooperates with the probability of labels by the output of models,which is to increase the accuracy of predict results on testing samples.We selected six popular deep learning models on three real datasets for the evaluation.The experimental results show that our system can achieve higher accuracy than state-of-art methods while reducing the dependency of labeled validation set.
基金National Natural Science Foundation of China(Grant Nos.61702281,61802279,6180021345 and 61702366)Natural Science Foundation of Tianjin(Grant Nos.18JCQNJC70300,19PTZWHZ00020,19JCTPJC49200 and 19JCYBJC15800)+3 种基金Fundamental Research Funds for the Tianjin Universities(Grant No.2019KJ019)the Tianjin Science and Technology Program(Grant No.19PTZWHZ00020)in part by the State Key Laboratory of ASIC and System(Grant No.2021KF014)Tianjin Educational Commission Scientific Research Program Project(Grant Nos.2018KJ215 and 2020KJ112).
文摘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 the selected models to get more accurate results.The experimental results show that our framework achieved higher accuracy than the existing methods.Our framework can be an option for the deep learning system to increase the classification accuracy.
