WO2025069242A1 - 情報処理装置、情報処理方法、及び記録媒体 - Google Patents

情報処理装置、情報処理方法、及び記録媒体 Download PDF

Info

Publication number
WO2025069242A1
WO2025069242A1 PCT/JP2023/035114 JP2023035114W WO2025069242A1 WO 2025069242 A1 WO2025069242 A1 WO 2025069242A1 JP 2023035114 W JP2023035114 W JP 2023035114W WO 2025069242 A1 WO2025069242 A1 WO 2025069242A1
Authority
WO
WIPO (PCT)
Prior art keywords
likelihood ratio
information processing
sequence data
loss function
learning
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2023/035114
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
章記 海老原
大輝 宮川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to PCT/JP2023/035114 priority Critical patent/WO2025069242A1/ja
Priority to JP2025548111A priority patent/JPWO2025069242A1/ja
Publication of WO2025069242A1 publication Critical patent/WO2025069242A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • This disclosure relates to the technical fields of information processing devices, information processing methods, and recording media.
  • Patent Document 1 discloses a device that classifies sequence data into one of a number of predefined classes by sequentially acquiring and analyzing multiple elements contained in the sequence data.
  • This disclosure aims to improve the related technology described above.
  • One aspect of the information processing device disclosed herein includes an acquisition means for sequentially acquiring multiple elements included in sequence data, a likelihood ratio calculation means for calculating a likelihood ratio indicating the likelihood of the class to which the sequence data belongs based on two or more adjacent elements each time an element is acquired, a classification means for classifying the sequence data into one of multiple classes based on the likelihood ratio, and a learning means for performing learning related to the calculation of the likelihood ratio using a sampling cost loss function related to the cost of acquiring the elements.
  • One aspect of the information processing method disclosed herein sequentially acquires multiple elements contained in sequence data, and for each element acquired, calculates a likelihood ratio indicating the likelihood of the class to which the sequence data belongs based on two or more adjacent elements, classifies the sequence data into one of multiple classes based on the likelihood ratio, and performs learning related to the calculation of the likelihood ratio using a sampling cost loss function related to the cost of acquiring the elements.
  • a computer program is recorded that causes a computer to execute an information processing method that sequentially acquires multiple elements contained in sequence data, and for each acquired element, calculates a likelihood ratio indicating the likelihood of the class to which the sequence data belongs based on two or more adjacent elements, classifies the sequence data into one of multiple classes based on the likelihood ratio, and performs learning related to the calculation of the likelihood ratio using a sampling cost loss function related to the cost of acquiring the elements.
  • FIG. 2 is a block diagram showing a hardware configuration of a first information processing apparatus.
  • FIG. 2 is a block diagram showing a functional configuration of a first information processing apparatus.
  • 10 is a flowchart showing a flow of a classification operation in the first information processing apparatus.
  • 10 is a flowchart showing a flow of a learning operation in the first information processing apparatus.
  • FIG. 2 is a block diagram showing a functional configuration of a second information processing apparatus.
  • 13 is a flowchart showing a flow of a learning operation in the second information processing apparatus. 13 is a graph showing an example of a decision-making time in a second information processing apparatus.
  • FIG. 1 First Embodiment The first embodiment will be described with reference to FIGS. 1 to 4.
  • Fig. 1 is a block diagram showing the hardware configuration of the first information processing apparatus.
  • the first information processing device 10 includes a processor 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and a storage device 14.
  • the information processing device 10 may further include an input device 15 and an output device 16.
  • the above-mentioned processor 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are each connected via a data bus 17.
  • the data bus 17 may be an interface other than a data bus (e.g., LAN, USB, etc.).
  • the processor 11 reads a computer program.
  • the processor 11 is configured to read a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14.
  • the processor 11 may read a computer program stored in a computer-readable storage medium using a storage medium reading device (not shown).
  • the processor 11 may obtain (i.e., read) a computer program from a device (not shown) disposed outside the information processing device 10 via a network interface.
  • the processor 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the computer program that the processor 11 reads.
  • a functional block that executes various processes for classifying sequence data is realized within the processor 11.
  • the processor 11 may function as a controller that executes each control in the information processing device 10.
  • the processor 11 may be configured as, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), or a quantum processor.
  • the processor 11 may be configured as one of these, or may be configured to use multiple processors in parallel.
  • RAM 12 temporarily stores computer programs executed by processor 11.
  • RAM 12 temporarily stores data that processor 11 uses temporarily while processor 11 is executing a computer program.
  • RAM 12 may be, for example, a D-RAM (Dynamic Random Access Memory) or an SRAM (Static Random Access Memory). Also, other types of volatile memory may be used instead of RAM 12.
  • ROM 13 stores computer programs executed by processor 11. ROM 13 may also store other fixed data. ROM 13 may be, for example, a P-ROM (Programmable Read Only Memory) or an EPROM (Erasable Read Only Memory). Also, other types of non-volatile memory may be used instead of ROM 13.
  • the storage device 14 stores data that the information processing device 10 stores long-term.
  • the storage device 14 may operate as a temporary storage device for the processor 11.
  • the storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.
  • the input device 15 is a device that receives input instructions from a user of the information processing device 10.
  • the input device 15 may include, for example, at least one of a keyboard, a mouse, and a touch panel.
  • the input device 15 may be configured as a mobile terminal such as a smartphone or a tablet.
  • the input device 15 may be, for example, a device that includes a microphone and is capable of voice input.
  • the output device 16 is a device that outputs information related to the information processing device 10 to the outside.
  • the output device 16 may be a display device (e.g., a display) that can display information related to the information processing device 10.
  • the output device 16 may also be a speaker or the like that can output information related to the information processing device 10 as audio.
  • the output device 16 may be configured as a mobile terminal such as a smartphone or a tablet.
  • FIG. 1 shows an example of an information processing device 10 that is configured to include multiple devices, all or some of these functions may be realized by a single device.
  • Such an information processing device may, for example, be configured to include only the above-mentioned processor 11, RAM 12, and ROM 13, and the other components (i.e., storage device 14, input device 15, output device 16, etc.) may be provided by, for example, an external device connected to the information processing device 10.
  • the information processing device 10 may have some of its calculation functions realized by an external device (for example, an external server or cloud, etc.).
  • Fig. 2 is a block diagram showing the functional configuration of the first information processing device.
  • the first information processing device 10 is configured as a device for classifying time series data.
  • the first information processing device 10 may be configured as a device that acquires images of time series data and classifies the type of object contained in the image.
  • the first information processing device 10 is configured to include an acquisition unit 50, a likelihood ratio calculation unit 100, a classification unit 150, and a learning unit 200 as components for realizing its functions.
  • Each of the acquisition unit 50, the likelihood ratio calculation unit 100, the classification unit 150, and the learning unit 200 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).
  • the acquisition unit 50 is configured to be able to acquire sequence data.
  • the sequence data here refers to data including multiple elements arranged in a predetermined order, and one example is time-series data. More specific examples of sequence data include, but are not limited to, video data, audio data, or subdivided image data.
  • the acquisition unit 50 is configured to be able to sequentially acquire multiple elements included in the sequence data.
  • the acquisition unit 50 may be configured to acquire elements included in the sequence data one by one in order.
  • the acquisition unit 50 may acquire data directly from any data acquisition device (e.g., a camera, a microphone, etc.), or may read data that has been acquired in advance by a data acquisition device and stored in storage, etc. When acquiring data from a camera, the acquisition unit 50 may be configured to acquire data from each of multiple cameras.
  • the likelihood ratio calculation unit 100 is configured to be able to calculate a likelihood ratio from the sequence data acquired by the acquisition unit 50.
  • the "likelihood ratio" here is an index indicating which of multiple classes that are classification candidates the sequence data belongs to (more specifically, an index indicating the likelihood of the class to which the sequence data belongs).
  • the likelihood ratio calculation unit 100 calculates a likelihood ratio each time an element is acquired. That is, the likelihood ratio calculation unit 100 calculates a likelihood ratio when the acquisition unit 50 acquires one element, and calculates a new likelihood ratio when the acquisition unit 50 acquires another element.
  • the likelihood ratio calculation unit 100 calculates a likelihood ratio based on two or more consecutive elements among the elements acquired sequentially by the acquisition unit 50.
  • the likelihood ratio calculation unit 100 may calculate a likelihood ratio using a newly acquired element and a previously acquired element or a previously calculated likelihood ratio.
  • the likelihood ratio calculation unit 100 may include a storage unit that stores previously acquired elements or previously calculated likelihood ratios.
  • the likelihood ratio calculation unit 100 is configured, for example, as a trained neural network.
  • the likelihood ratio calculation unit 100 is configured to be trained by a learning unit 200, which will be described later.
  • the classification unit 150 classifies the sequence data into one of a plurality of classes based on the likelihood ratio calculated by the likelihood ratio calculation unit 100. Specifically, the classification unit 150 classifies the sequence data into one of a plurality of classes by comparing the likelihood ratio calculated by the likelihood ratio calculation unit 100 with a preset threshold. For example, the classification unit 150 classifies the sequence data into class A when the likelihood ratio exceeds a threshold corresponding to class A. Furthermore, the classification unit 150 classifies the sequence data into class B when the likelihood ratio exceeds a threshold corresponding to class B.
  • the classification unit 150 may classify, for example, whether a person's face in an image is a real face or a fake face (for example, impersonation using a photograph or a 3D mask). Furthermore, the plurality of classes may be three or more. In this case, the classification unit 150 may perform classification using a threshold set for each class.
  • the learning unit 200 is configured to be able to execute learning related to the calculation of likelihood ratios in the likelihood ratio calculation unit 100. That is, learning related to the calculation of likelihood ratios is executed so that class classification based on likelihood ratios can be performed quickly and accurately.
  • the learning unit 200 executes learning using a loss function. Specifically, the learning unit 200 optimizes the parameters of a model used when calculating likelihood ratios using the loss function. Note that existing technology can be appropriately adopted as a parameter optimization method using a loss function. An example of an optimization method is the backpropagation method, but other methods may also be used.
  • the learning unit 200 also includes a sampling cost loss function calculation unit 210.
  • the sampling cost loss function calculation unit 210 calculates a sampling cost loss function, which is a loss function used for learning.
  • the sampling cost loss function is a loss function related to the cost of acquiring elements (hereinafter, appropriately referred to as "sampling cost").
  • sampling cost loss function may be a function including a preset cost parameter. Specific examples of the sampling cost loss function will be explained in other embodiments described later.
  • a classification operation i.e., an operation of classifying sequence data into one of a plurality of classes
  • Fig. 3 is a flowchart showing the flow of the classification operation in the first information processing device.
  • the acquisition unit 50 first acquires one element contained in the sequence data (step S101). Then, the likelihood ratio calculation unit 100 calculates a likelihood ratio based on the element acquired by the acquisition unit 50 (step S102).
  • the classification unit 150 determines whether there is a class for which the likelihood ratio calculated by the likelihood ratio calculation unit 100 exceeds a threshold value (step S103). That is, the classification unit 150 compares the likelihood ratio calculated by the likelihood ratio calculation unit 100 with the threshold value corresponding to each class that is a classification candidate, and determines whether the likelihood ratio exceeds the threshold value corresponding to any class.
  • the likelihood ratio calculated by the likelihood ratio calculation unit 100 tends to approach the threshold value corresponding to the class to be classified each time an element is acquired. Therefore, by repeating the process while acquiring elements one by one as described above, the sequence data can be classified into an appropriate class. At this time, for sequence data that is easy to classify, the threshold value is exceeded at an early stage, so the sequence data can be classified early. On the other hand, for sequence data that is difficult to classify, elements continue to be acquired until the threshold value is exceeded, so the sequence data can be classified accurately over a period of time.
  • learning related to the calculation of likelihood ratios is performed using a sampling cost loss function.
  • the cost of obtaining elements in other words, the penalty for the time it takes to classify
  • the penalty for the time it takes to classify is taken into account, making it possible to perform more appropriate learning.
  • it becomes possible to accurately classify sequence data more quickly i.e., with as few elements as possible).
  • Fig. 5 is a block diagram showing the functional configuration of the second information processing device.
  • the same reference numerals are used to designate the same elements as those shown in Fig. 2.
  • the classification unit 150 determines the decision-making time ⁇ , which is the time when the likelihood ratio calculated by the likelihood ratio calculation unit 100 exceeds a threshold value (step S253).
  • the decision-making time ⁇ will be described in detail below with reference to FIG. 7.
  • FIG. 7 is a graph showing an example of a decision-making time in the second information processing device.
  • the information processing device described in Supplementary Note 2 is the information processing device described in Supplementary Note 1, wherein the classification means classifies the sequence data when the likelihood ratio exceeds any of thresholds corresponding to each of the multiple classes, and the sampling cost loss function is a function of the time at which the likelihood ratio exceeds the threshold.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)
PCT/JP2023/035114 2023-09-27 2023-09-27 情報処理装置、情報処理方法、及び記録媒体 Ceased WO2025069242A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2023/035114 WO2025069242A1 (ja) 2023-09-27 2023-09-27 情報処理装置、情報処理方法、及び記録媒体
JP2025548111A JPWO2025069242A1 (cg-RX-API-DMAC7.html) 2023-09-27 2023-09-27

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2023/035114 WO2025069242A1 (ja) 2023-09-27 2023-09-27 情報処理装置、情報処理方法、及び記録媒体

Publications (1)

Publication Number Publication Date
WO2025069242A1 true WO2025069242A1 (ja) 2025-04-03

Family

ID=95202393

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/035114 Ceased WO2025069242A1 (ja) 2023-09-27 2023-09-27 情報処理装置、情報処理方法、及び記録媒体

Country Status (2)

Country Link
JP (1) JPWO2025069242A1 (cg-RX-API-DMAC7.html)
WO (1) WO2025069242A1 (cg-RX-API-DMAC7.html)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021220450A1 (ja) * 2020-04-30 2021-11-04 日本電気株式会社 識別装置、識別方法及び記録媒体
WO2021229662A1 (ja) * 2020-05-11 2021-11-18 日本電気株式会社 判定装置、判定方法および記録媒体
WO2023148846A1 (ja) * 2022-02-02 2023-08-10 日本電気株式会社 情報処理装置、情報処理方法、及び記録媒体

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021220450A1 (ja) * 2020-04-30 2021-11-04 日本電気株式会社 識別装置、識別方法及び記録媒体
WO2021229662A1 (ja) * 2020-05-11 2021-11-18 日本電気株式会社 判定装置、判定方法および記録媒体
WO2023148846A1 (ja) * 2022-02-02 2023-08-10 日本電気株式会社 情報処理装置、情報処理方法、及び記録媒体

Also Published As

Publication number Publication date
JPWO2025069242A1 (cg-RX-API-DMAC7.html) 2025-04-03

Similar Documents

Publication Publication Date Title
CN111461168B (zh) 训练样本扩充方法、装置、电子设备及存储介质
CN109711548B (zh) 超参数的选取方法、使用方法、装置及电子设备
CN109214343B (zh) 用于生成人脸关键点检测模型的方法和装置
JP7740389B2 (ja) 情報処理装置、情報処理方法、及び記録媒体
CN108121986A (zh) 目标检测方法及装置、计算机装置和计算机可读存储介质
CN110196908A (zh) 数据分类方法、装置、计算机装置及存储介质
CN112149615A (zh) 人脸活体检测方法、装置、介质及电子设备
WO2020244075A1 (zh) 手语识别方法、装置、计算机设备及存储介质
CN111160959B (zh) 一种用户点击转化预估方法及装置
CN115035017B (zh) 细胞密度分群方法、装置、电子设备及存储介质
WO2020244151A1 (zh) 图像处理方法、装置、终端及存储介质
CN110969200A (zh) 基于一致性负样本的图像目标检测模型训练方法及装置
CN115004245A (zh) 目标检测方法、装置、电子设备和计算机存储介质
EP4141806A1 (en) Hand-drawn diagram recognition using visual arrow-relation detection
JP2019220014A (ja) 画像解析装置、画像解析方法及びプログラム
CN114241411B (zh) 基于目标检测的计数模型处理方法、装置及计算机设备
US11715204B2 (en) Adaptive machine learning system for image-based biological sample constituent analysis
CN113902001A (zh) 一种模型训练方法、装置、电子设备及存储介质
JPWO2018168515A1 (ja) 画像処理装置、画像処理方法及び記録媒体
CN114549889A (zh) 细胞密度分类方法及装置、电子装置及存储介质
WO2025069245A1 (ja) 情報処理装置、情報処理方法、及び記録媒体
CN113807407B (zh) 目标检测模型训练方法、模型性能检测方法及装置
CN115578563A (zh) 一种图像分割方法、系统、存储介质和电子设备
JP2023065855A (ja) 情報処理装置、情報処理方法およびプログラム
WO2024079853A1 (ja) 情報処理装置、情報処理方法、及び記録媒体

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23954218

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2025548111

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2025548111

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE