Method, apparatus, and non-temporary computer-readable medium

Abstract

A method for causing one or more processors to execute: performing learning of a first model of a capsule network type including one or more capsule layers each having one or more capsules to reproduce correspondence between a plurality of first data elements included in a first data set and a pre-label corresponding to each of the plurality of first data elements; and inputting the first data set into the learned first model and acquiring first intermediate data based on at least one of a first activation and a first pose included in the one or more capsules, for the one or more capsule layers.

What is claimed is: 
     
         1 . A method for causing one or more processors to execute:
 performing learning of a first model of a capsule network type including one or more capsule layers each having one or more capsules to reproduce correspondence between a plurality of first data elements included in a first data set and a pre-label corresponding to each of the plurality of first data elements; and   inputting the first data set into the learned first model and acquiring first intermediate data based on at least one of a first activation and a first pose included in the one or more capsules, for the one or more capsule layers.   
     
     
         2 . A method for causing one or more processors to execute using a first model learned in advance, in which the first model is a capsule network type including one or more capsule layers each having one or more capsules, and is learned to reproduce correspondence between a plurality of first data elements included in a first data set and a pre-label corresponding to each of the plurality of first data elements,
 the method comprising:
 acquiring first intermediate data based on at least one of a first activation and a first pose included in the one or more capsules, for each of the one or more capsule layers when the first data set is input into the learned first model; 
 inputting a second data element into the first model and acquiring second intermediate data based on at least one of a second activation and a second pose included in the one or more capsules, for each of the one or more capsule layers; and 
 calculating a similarity between the first intermediate data and the second intermediate data, for the one or more capsule layers. 
   
     
     
         3 . The method according to  claim 2 , further comprising:
 outputting information about the calculated similarity.   
     
     
         4 . The method according to  claim 2 , further comprising:
 inputting the second data element into the first model to discriminate a label of the second data element.   
     
     
         5 . The method according to  claim 4 , further comprising:
 outputting a discrimination result of the label.   
     
     
         6 . The method according to  claim 2 , wherein
 the capsule layer has a plurality of the capsules,   the acquiring of the first intermediate data includes acquiring the first intermediate data included in each of the plurality of capsules, and   associating a first partial range, which is a part of the first data element corresponding to the acquired first intermediate data, with the corresponding first intermediate data,   the acquiring of the second intermediate data includes   acquiring the second intermediate data included in each of the plurality of capsules, and   associating a second partial range, which is a part of the second data element corresponding to the acquired second intermediate data, with the corresponding second intermediate data, and   the calculating of the similarity includes calculating the similarity between the first intermediate data of the first partial range and the second intermediate data of the second partial range corresponding to the first partial range.   
     
     
         7 . The method according to  claim 6 , wherein
 the information about the similarity includes partial range information indicating the first partial range and the second partial range in which the similarity calculation is performed.   
     
     
         8 . The method according to  claim 6 , wherein
 the capsule layer has a hierarchy structure configured of a plurality of layers, and   the calculating of the similarity includes   calculating the similarity between the first intermediate data of the first partial range and the second intermediate data of the second partial range corresponding to the first partial range, in each capsule layer.   
     
     
         9 . The method according to  claim 2 , wherein
 the capsule layer has a plurality of the capsules,   the acquiring of the first intermediate data includes acquiring the first intermediate data included in each of the plurality of capsules, and   associating a first partial range, which is a part of the first data element corresponding to the acquired first intermediate data, with the corresponding first intermediate data,   the acquiring of the second intermediate data includes   acquiring the second intermediate data included in each of the plurality of capsules, and   associating a second partial range, which is a part of the second data element corresponding to the acquired second intermediate data, with the corresponding second intermediate data, and   the calculating of the similarity includes calculating the similarity between the first intermediate data and the second intermediate data.   
     
     
         10 . The method according to  claim 9 , wherein
 the information about the similarity includes partial range information indicating the second partial range in which the similarity calculation is performed.   
     
     
         11 . The method according to  claim 9 , wherein
 the information about the similarity includes partial range information indicating the first partial range and the second partial range in which the similarity calculation is performed.   
     
     
         12 . The method according to  claim 9 , wherein
 the capsule layer has a hierarchy structure configured of a plurality of layers, and   the calculating of the similarity includes   calculating the similarity between the first intermediate data and the second intermediate data in each capsule layer.   
     
     
         13 . The method according to  claim 8 , wherein
 the information about the similarity further includes at least one of layer label information for identifying a hierarchy of a plurality of the capsule layers, similarity information indicating the similarity for each hierarchy, hierarchy partial range information indicating a hierarchy partial range which is the second partial range in which the similarity calculation is performed in each hierarchy, and comparison information indicating a magnitude relationship between the similarity and a predetermined threshold value.   
     
     
         14 . The method according to  claim 2 , wherein
 the first intermediate data includes at least the first pose,   the second intermediate data includes at least the second pose, and   the calculating of the similarity includes calculating the similarity between the first pose and the second pose.   
     
     
         15 . The method according to  claim 2 , wherein
 the first intermediate data includes at least the first activation,   the second intermediate data includes at least the second activation, and   the calculating of the similarity includes calculating the similarity between the first activation and the second activation.   
     
     
         16 . The method according to  claim 2 , wherein
 the first intermediate data includes the first pose and the first activation,   the second intermediate data includes the second pose and the second activation, and   the calculating of the similarity includes weighting the first pose by the first activation, weighting the second pose by the second activation, and calculating the similarity between the weighted first pose and the weighted second pose.   
     
     
         17 . An apparatus comprising:
 one or more processors, wherein   the one or more processors is configured to execute:   performing learning of a first model of a capsule network type including one or more capsule layers each having one or more capsules to reproduce correspondence between a plurality of first data elements included in a first data set and a pre-label corresponding to each of the plurality of first data elements; and   inputting the first data set into the learned first model and acquiring first intermediate data based on at least one of a first activation and a first pose included in the one or more capsules, for the one or more capsule layers.   
     
     
         18 . An apparatus comprising:
 a storage device which is a capsule network type including one or more capsule layers each having one or more capsules, and stores a first model learned to reproduce correspondence between a plurality of first data elements included in a first data set and a pre-label corresponding to each of the plurality of first data elements; and   one or more processors, wherein   the one or more processors is configured to execute:   acquiring first intermediate data based on at least one of a first activation and a first pose included in the one or more capsules, for each of the one or more capsule layers when the first data set is input into the learned first model;   inputting a second data element into the first model and acquiring second intermediate data based on at least one of a second activation and a second pose included in the one or more capsules, for each of the one or more capsule layers; and   calculating a similarity between the first intermediate data and the second intermediate data, for the one or more capsule layers.   
     
     
         19 . A non-temporary computer-readable medium storing instructions for causing one or more processors to execute:
 performing learning of a first model of a capsule network type including one or more capsule layers each having one or more capsules to reproduce correspondence between a plurality of first data elements included in a first data set and a pre-label corresponding to each of the plurality of first data elements; and   inputting the first data set into the learned first model and acquiring first intermediate data based on at least one of a first activation and a first pose included in the one or more capsules, for each of the one or more capsule layers.   
     
     
         20 . A non-temporary computer-readable medium storing instructions for causing one or more processors to execute using a first model learned in advance, wherein
 the first model is a capsule network type including one or more capsule layers each having one or more capsules, and is learned to reproduce correspondence between a plurality of first data elements included in a first data set and a pre-label corresponding to each of the plurality of first data elements,   the instructions causes one or more processors to further execute:   acquiring first intermediate data based on at least one of a first activation and a first pose included in the one or more capsules, for each of the one or more capsule layers when the first data set is input into the learned first model;   inputting a second data element into the first model and acquiring second intermediate data based on at least one of a second activation and a second pose included in the one or more capsules, for each of the one or more capsule layers; and   calculating a similarity between the first intermediate data and the second intermediate data for the one or more capsule layers.