# US 2025/0166356 A1 · Learning device, learning method, and recording medium

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

- Number: US 2025/0166356 A1
- Document ID: US20250166356A1
- Status: Published application
- Kind: A1
- Application number: 18/841,744
- Filed: 2022-03-04
- Published: 2025-05-22
- Earliest claimed: 2022-03-04
- Assignees: NEC Corporation; University of Tsukuba
- Applicants: NEC Corporation; University of Tsukuba
- Inventors: Kazuya KAKIZAKI; Kazuto FUKUCHI; Jun SAKUMA
- Web page: https://patentgrep.com/patent/US20250166356A1

## CPC

- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06F 16/583: using metadata automatically derived from the content
- G06N 20/00: Machine learning
- G06T 7/00: Image analysis
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 10/778: Active pattern-learning, e.g. online learning of image or video features
- G06V 10/82: using neural networks
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A learning device causes a feature amount extractor to be trained such that the upper limit and the lower limit of a distance, obtained in a case where the feature amount extractor is used, in a feature space between images become close to the distance.

## Claims

### Claim 1

A learning device comprising:
at least one memory configured to store instructions; and
at least one processor configured to execute the instructions to:
cause a feature amount extractor to be trained such that the upper limit and the lower limit of a distance, obtained in a case where the feature amount extractor is used, in a feature space between images become close to the distance.

### Claim 2 (depends on 1)

The learning device according to claim 1,
wherein the at least one processor is configured to execute the instructions to cause the feature amount extractor to be trained by minimizing a loss function.

### Claim 3 (depends on 2)

The learning device according to claim 2,
wherein the at least one processor is configured to execute the instructions to cause the feature amount extractor to be trained by minimizing the loss function that includes a term representing the difference between the distance and the upper limit of the distance and a term representing the difference between the distance and the lower limit of the distance in the feature space between the images.

### Claim 4 (depends on 2)

The learning device according to claim 2,
wherein the at least one processor is configured to execute the instructions to cause the feature amount extractor to be trained by minimizing the loss function that includes a term representing an upper limit of the distance in the feature space between the same images.

### Claim 5 (depends on 2)

The learning device according to claim 2,
wherein the at least one processor is configured to execute the instructions to cause the feature amount extractor to be trained by using triplet loss to minimize the loss function including a term representing the difference between the distance in the feature space and the upper limit of the distance for an anchor image and a positive sample image, as well as a term representing the difference between the distance and the lower limit of the distance for the anchor image and a negative sample image.

### Claim 6 (depends on 2)

The learning device according to claim 2,
wherein the at least one processor is configured to execute the instructions to cause the feature amount extractor to be trained by using triplet loss to minimize the loss function so as to make the upper limit of the distance between the anchor image and the positive sample image closer and the lower limit of the distance between the anchor image and the negative sample image farther.

### Claim 7 (depends on 3)

The learning device according to claim 3,
wherein the image is an image included in a candidate image group used for content-based image retrieval.

### Claim 8 (depends on 7)

The learning device according to claim 7,
wherein the at least one processor is configured to execute the instructions to cause the feature amount extractor to be trained by minimizing the loss function that includes a term representing the distance between the feature amount of an image using a feature amount extractor before updating and the feature amount of the image using the feature amount extractor to be updated.

### Claim 9 (depends on 1)

The learning device according to claim 1,
wherein the upper limit and lower limit of the distance in the feature space between images x1 and x2 are calculated by the following Expressions, respectively,
d
¯
(
f
⁡
(
x
1
)
,
f
⁡
(
x
2
)
)
=
(
∑
i
max
⁡
(
❘
"\[LeftBracketingBar]"
f
¯
(
x
1
)
i
-
f
⁡
(
x
2
)
i
❘
"\[RightBracketingBar]"
1
,
❘
"\[LeftBracketingBar]"
f
⁡
(
x
2
)
i
-
f
¯
(
x
1
)
i
❘
"\[RightBracketingBar]"
1
)
2
)
1
2
[
Expression
⁢
1
]
d
¯
(
f
⁡
(
x
1
)
,
f
⁡
(
x
2
)
)
=
(
∑
i
min
⁡
(
0
,
f
¯
(
x
1
)
i
-
f
⁡
(
x
2
)
i
,
f
⁡
(
x
2
)
i
-
f
¯
(
x
1
)
i
)
2
)
1
2
[
Expression
⁢
2
]
where i represents the i-th element in a case where the image is mapped by the feature amount extractor to an n-dimensional vector in the feature space.

### Claim 10

A learning method comprising:
causing a feature amount extractor to be trained such that the upper limit and the lower limit of a distance, obtained in a case where the feature amount extractor is used, in a feature space between images become close to the distance.

### Claim 11

A non-transitory recording medium that records a program for causing a computer to execute:
causing a feature amount extractor to be trained such that the upper limit and the lower limit of a distance, obtained in a case where the feature amount extractor is used, in a feature space between images become close to the distance.
