专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11514272B2 Apparatus and method for training classification model and apparatus for performing classification by using classification model 有权
公开(公告)号：US11514272B2
公开(公告)日：2022-11-29
申请号：US16736180
申请日：2020-01-07
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu
IPC分类号： G06K9/62 , G06N20/00 , G06N3/08
摘要： An apparatus for training a classification model includes: a feature extraction unit configured to set, with respect to each training set of a first predetermined number of training sets, feature extraction layers, and extract features of a sample image, where at least two of the training sets at least partially overlap; a feature fusion unit configured to set, with respect to training set, feature fusion layers, and perform a fusion on the extracted features of the sample image; and a loss determination unit configured to set, with respect to training set, a loss determination layer, calculate a loss function of the sample image based on the fused feature of the sample image, and train a classification model based on the loss function. The first predetermined number of training sets share at least one layer of feature fusion layers and feature extraction layers set with respect to each training set.

2. 发明授权

US11113581B2 Information processing method and information processing apparatus 有权
公开(公告)号：US11113581B2
公开(公告)日：2021-09-07
申请号：US16450153
申请日：2019-06-24
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu
IPC分类号： G06K9/62 , G06N3/08
摘要： The present disclosure relates to an information processing method and an information processing apparatus. The information processing method according to the present disclosure performs training on a classification model by using a plurality of training samples, and comprises the steps of: adjusting a distribution of feature vectors of the plurality of training samples in a feature space based on a typical sample in the plurality of training samples; and performing training on the classification model by using the adjusted feature vectors of the plurality of training samples. Through the technology according to the present disclosure, it is possible to perform pre-adjustment on training samples before training, such that it is possible to reduce discrimination between training samples belonging to a same class and increase discrimination between training samples belonging to different classes in the training process. The classification model trained as such is capable of performing accurate classification on samples acquired under an extreme condition.

3. 发明申请

US20200265220A1 APPARATUS AND METHOD FOR TRAINING CLASSIFICATION MODEL AND APPARATUS FOR CLASSIFYING WITH CLASSIFICATION MODEL 审中-公开
公开(公告)号：US20200265220A1
公开(公告)日：2020-08-20
申请号：US16738393
申请日：2020-01-09
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu
IPC分类号： G06K9/00 , G06K9/62 , G06N3/08
摘要： An apparatus and method for training a classification model and an apparatus for classifying with a classification model are disclosed. The apparatus for training a classification model comprises: a local area obtainment unit to, obtain predetermined local area of each sample image; a feature extraction unit to, with respect to each sample image, set corresponding numbers of feature extraction layers for the global area and each predetermined local area, to extract a global feature of the global area and a local feature of each predetermined local area, wherein the global area and the predetermined local areas share at least one feature extraction layer in which the global feature and each local feature are combined; and a loss determination unit to calculate a loss function of the sample image based on combined features of each sample image, and to train the classification model based on the loss function.

4. 发明申请

US20200265272A1 APPARATUS AND METHOD FOR TRAINING CLASSIFICATION MODEL AND APPARATUS FOR PERFORMING CLASSIFICATION BY USING CLASSIFICATION MODEL 审中-公开
公开(公告)号：US20200265272A1
公开(公告)日：2020-08-20
申请号：US16736180
申请日：2020-01-07
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu
IPC分类号： G06K9/62 , G06N3/08 , G06N20/00
摘要： An apparatus for training a classification model includes: a feature extraction unit configured to set, with respect to each training set of a first predetermined number of training sets, feature extraction layers, and extract features of a sample image, where at least two of the training sets at least partially overlap; a feature fusion unit configured to set, with respect to training set, feature fusion layers, and perform a fusion on the extracted features of the sample image; and a loss determination unit configured to set, with respect to training set, a loss determination layer, calculate a loss function of the sample image based on the fused feature of the sample image, and train a classification model based on the loss function. The first predetermined number of training sets share at least one layer of feature fusion layers and feature extraction layers set with respect to each training set.

5. 发明申请

US20200234068A1 APPARATUS AND METHOD FOR TRAINING CLASSIFYING MODEL 审中-公开
公开(公告)号：US20200234068A1
公开(公告)日：2020-07-23
申请号：US16737370
申请日：2020-01-08
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu
IPC分类号： G06K9/00 , G06K9/62
摘要： An apparatus for training a classifying model comprises: a first obtaining unit configured to input a sample image to a first machine learning framework, to obtain a first classification probability and a first classification loss; a second obtaining unit configured to input a second image to a second machine learning framework, to obtain a second classification probability and a second classification loss, the two machine learning frameworks having identical structures and sharing identical parameters; a similarity loss calculating unit configured to calculate a similarity loss related to a similarity between the first classification probability and the second classification probability; a total loss calculating unit configured to calculate the sum of the similarity loss, the first classification loss and the second classification loss, as a total loss; and a training unit configured to adjust parameters of the two machine learning frameworks to obtain a trained classifying model.

6. 发明授权

US11270139B2 Apparatus and method for training classifying model 有权
公开(公告)号：US11270139B2
公开(公告)日：2022-03-08
申请号：US16737370
申请日：2020-01-08
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu
IPC分类号： G06K9/00 , G06K9/62
摘要： An apparatus for training a classifying model comprises: a first obtaining unit configured to input a sample image to a first machine learning framework, to obtain a first classification probability and a first classification loss; a second obtaining unit configured to input a second image to a second machine learning framework, to obtain a second classification probability and a second classification loss, the two machine learning frameworks having identical structures and sharing identical parameters; a similarity loss calculating unit configured to calculate a similarity loss related to a similarity between the first classification probability and the second classification probability; a total loss calculating unit configured to calculate the sum of the similarity loss, the first classification loss and the second classification loss, as a total loss; and a training unit configured to adjust parameters of the two machine learning frameworks to obtain a trained classifying model.

7. 发明授权

US11113513B2 Apparatus and method for training classification model and apparatus for classifying with classification model 有权
公开(公告)号：US11113513B2
公开(公告)日：2021-09-07
申请号：US16738393
申请日：2020-01-09
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu
IPC分类号： G06K9/46 , G06K9/00 , G06K9/62 , G06N3/08
摘要： An apparatus and method for training a classification model and an apparatus for classifying with a classification model are disclosed. The apparatus for training a classification model comprises: a local area obtainment unit to, obtain predetermined local area of each sample image; a feature extraction unit to, with respect to each sample image, set corresponding numbers of feature extraction layers for the global area and each predetermined local area, to extract a global feature of the global area and a local feature of each predetermined local area, wherein the global area and the predetermined local areas share at least one feature extraction layer in which the global feature and each local feature are combined; and a loss determination unit to calculate a loss function of the sample image based on combined features of each sample image, and to train the classification model based on the loss function.

8. 发明申请

US20210142150A1 INFORMATION PROCESSING DEVICE AND METHOD, AND DEVICE FOR CLASSIFYING WITH MODEL 有权
公开(公告)号：US20210142150A1
公开(公告)日：2021-05-13
申请号：US17090032
申请日：2020-11-05
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Fei Li , Rujie Liu
IPC分类号： G06N3/04 , G06K9/62
摘要： An information processing device and method, and a device for classifying with a model are provided. The information processing device includes a first training unit being configured to train a first model using a first training sample set, to obtain a trained first model; a second training unit being configured to train the trained first model using a second training sample set while maintaining a predetermined portion of characteristics of the trained first model, to obtain a trained second model, and a third training unit being configured to train a third model using the second training sample set while causing a difference between classification performances of the trained second model and the third model to be within a first predetermined range, to obtain a trained third model as a final model.

9. 发明申请

US20190138854A1 METHOD AND APPARATUS FOR TRAINING FACE RECOGNITION MODEL 审中-公开
公开(公告)号：US20190138854A1
公开(公告)日：2019-05-09
申请号：US16179292
申请日：2018-11-02
申请人： Fujitsu Limited
发明人： Meng Zhang , Rujie Liu , Jun Sun
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6262 , G06K9/00281 , G06K9/00288 , G06K9/6256
摘要： A method and apparatus for removing black eyepits and sunglasses in first actual scenario data having an image containing a face acquired from an actual scenario, to obtain second actual scenario data; counting a proportion of wearing glasses in the second actual scenario data; dividing original training data composed of an image containing a face into wearing-glasses and not-wearing-glasses first and second training data, where a proportion of wearing glasses in the original training data is lower than a proportion in the second actual scenario data; generating wearing-glasses third training data based on glasses data and the second training data; generating fourth training data in which a proportion of wearing glasses is equal to the proportion of wearing glasses in the second actual scenario data, based on the third training data and the original training data; and training a face recognition model based on the fourth training data.

10. 发明授权

US11514264B2 Method and apparatus for training classification model, and classification method 有权
公开(公告)号：US11514264B2
公开(公告)日：2022-11-29
申请号：US17076320
申请日：2020-10-21
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Fei Li , Rujie Liu
IPC分类号： G06K9/62 , G06N3/08
摘要： A method for training a classification model includes: performing training on the classification model using first and second sample sets, to calculate a classification loss; extracting a weight vector and a feature vector of each sample; calculating a mean weight vector and a mean feature vector of all samples in the first sample set; calculating a weight loss based on a difference of the weight vector of each sample in the second sample set from the mean weight vector, and calculating a feature loss based on a difference of a feature vector of each sample in the second sample set from the mean feature vector; calculating a total loss of the classification model based on the classification loss and at least one of the feature loss and the weight loss; and adjusting a parameter of the classification model until a predetermined condition is satisfied.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式