# US 2025/0166362 A1 · Learning apparatus, learning method and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0166362 A1
- Document ID: US20250166362A1
- Status: Published application
- Kind: A1
- Application number: 18/843,116
- Filed: 2022-03-30
- Published: 2025-05-22
- Earliest claimed: 2022-03-30
- Assignees: NEC Corporation
- Applicants: NEC Corporation
- Inventors: Masashi Usami; Koichi Takahashi
- Web page: https://patentgrep.com/patent/US20250166362A1

## CPC

- G06V 10/778: Active pattern-learning, e.g. online learning of image or video features
- G06N 3/08: Learning methods
- G06N 20/00: Machine learning
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/172: {Classification, e.g. identification}
- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06V 40/168: {Feature extraction; Face representation}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A learning apparatus learns a classifier model that performs multi-class classification of single-label or multi-labels for images, and includes: a learning unit that performs learning of the classifier model using a feature amount extracted from an image for learning as an input; and a margin giving unit that gives a margin to a loss function used for learning, wherein the margin giving unit fixes a total amount of margin to be given for the single-label or the multi-label, and gives a class margin obtained by asymmetrically distributing the total amount of the margin to each of a plurality of classes of the single-label or the multi-labels.

## Claims

### Claim 1

A learning apparatus that learns a classifier model that performs multi-class classification of single-label or multi-labels for images, the learning apparatus comprising:
a memory configured to store instructions; and
a processor configured to execute the instructions to:
perform learning of the classifier model using a feature amount extracted from an image for learning as an input; and
give a margin to a loss function used for learning, wherein the processor is further configured to execute the instructions to fix a total amount of margin to be given for the single-label or the multi-label, and give a class margin obtained by asymmetrically distributing the total amount of the margin to each of a plurality of classes of the single-label or the multi-labels.

### Claim 2 (depends on 1)

The learning apparatus according to claim 1, wherein the processor is further configured to execute the instructions to perform multi-class classification for each of the multi-labels.

### Claim 3 (depends on 1)

The learning apparatus according to claim 1, wherein the learning processor is further configured to execute the instructions to perform the learning of the classifier model by angular metric learning.

### Claim 4 (depends on 1)

The learning apparatus according to claim 1, wherein the processor is further configured to execute the instructions to give the class margin based on a proportion of samples of the class.

### Claim 5 (depends on 1)

The learning apparatus according to claim 1, wherein the processor is further configured to execute the instructions to give the class margin to the loss function, the class margin being calculated by the following Expression (1).
[
Math
.
1
]
m
a
,
c
⁢
(
γ
a
)
=
α
a
,
c
⁢
(
γ
a
)
×
m
a
(
1
)
(In Expression (1), ma is the total margin determined for the a-th label. αa,c (γa) is calculated by the following Expression (2).
[
Math
.
2
]
α
a
,
c
⁢
(
γ
a
)
=
exp
⁢
(
γ
a
⁢
sN
a
,
c
)
∑
c
″
∈
C
⁢
exp
⁢
(
γ
a
⁢
sN
a
,
c
″
)
(
2
)
In Expression 2, Na,c represents a proportion of the number of samples the c-th class in the a-th label. Na,c″ represents a proportion of the number of samples the c″-th class (c″ is an integer satisfying 1≤c″≤C) in the a-th label. The sum sign of the right-hand denominator in Expression (2) means the sum of all integers satisfying 1≤c″≤C. s is a hyperparameter.)

### Claim 6 (depends on 1)

The learning apparatus according to claim 1, wherein the processor is further configured to execute the instructions to automatically determine at least one of the ma and the ya.

### Claim 7 (depends on 1)

The learning apparatus according to claim 1, wherein the loss function is a loss function of Softmax type.

### Claim 8 (depends on 7)

The learning apparatus according to claim 7, wherein the processor is further configured to execute the instructions to give the class margin to be subtracted from cosine of an angle formed by a feature vector extracted from the image as a feature quantity and a representative vector of the class in the loss function of Softmax type.

### Claim 9 (depends on 7)

The learning apparatus according to claim 7, wherein the processor is further configured to execute the instructions to give the class margin to be added to an angle formed by a feature vector extracted from the image as the feature quantity and a representative vector of the class in the loss function of Softmax type.

### Claim 10 (depends on 7)

The learning apparatus according to claim 7, wherein the processor is further configured to execute the instructions to give the class margin to be multiplied to an angle formed by a feature vector extracted from the image as the feature quantity and a representative vector of the class in the loss function of Softmax type.

### Claim 11 (depends on 1)

The learning apparatus according to claim 1, wherein the processor is further configured to extract the feature amount by convolutional neural network.

### Claim 12 (depends on 1)

The learning apparatus according to claim 1, wherein the image is a face image.

### Claim 13 (depends on 1)

An estimating apparatus comprising:
a memory configured to store instructions; and
a processor configured to execute the instructions to:
acquire an image;
perform multi-class classification for the image by the classifier model learned by the learning apparatus according to claim 1.

### Claim 14

A learning method that learns a classifier model that performs multi-class classification of single-label or multi-labels for images, the learning method comprising:
performing learning of the classifier model using a feature amount extracted from an image for learning as an input; and
giving a margin to a loss function used for learning,
wherein giving the margin fixes a total amount of margin to be given for the single-label or the multi-label, and gives a class margin obtained by asymmetrically distributing the total amount of the margin to each of a plurality of classes of the single-label or the multi-labels.

### Claim 15

A non-transitory storage medium storing a program that causes a computer to perform: a learning method that learns a classifier model that performs multi-class classification of single-label or multi-labels for images, the learning method comprising:
performing learning of the classifier model using a feature amount extracted from an image for learning as an input; and
giving a margin to a loss function used for learning,
wherein giving the margin fixes a total amount of margin to be given for the single-label or the multi-label, and gives a class margin obtained by asymmetrically distributing the total amount of the margin to each of a plurality of classes of the single-label or the multi-labels.
