# US 2025/0148262 A1 · Method and apparatus with feature-level ensemble model

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

- Number: US 2025/0148262 A1
- Document ID: US20250148262A1
- Status: Published application
- Kind: A1
- Application number: 18/642,167
- Filed: 2024-04-22
- Published: 2025-05-08
- Earliest claimed: 2023-11-03
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Wonjun CHOI; Byung In YOO; Dongwook LEE
- Web page: https://patentgrep.com/patent/US20250148262A1

## CPC

- G06N 3/045: Combinations of networks
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and apparatus with a feature-level ensemble model are provided. A method of operating an ensemble model based on feature-level consolidation includes: obtaining queries by inputting a same input data item to respective transformer models, the transformer models generating respective queries from the input data item; forming an ensemble query corresponding to the queries; and generating a predicted value of the input data item by applying the ensemble query to a prediction model that includes a transformer decoder, the prediction model inferring the predicted value from the ensemble query.

## Claims

### Claim 1

A method of operating an ensemble model based on feature-level consolidation, the method comprising:
obtaining queries by inputting a same input data item to respective transformer models, the transformer models generating respective queries from the input data item;
forming an ensemble query corresponding to the queries; and
generating a predicted value of the input data item by applying the ensemble query to a prediction model that comprises a transformer decoder, the prediction model inferring the predicted value from the ensemble query.

### Claim 2 (depends on 1)

The method of claim 1, wherein the forming of the ensemble query corresponding to the queries comprises:
inputting the queries to respective projection networks that project the queries to respective projected queries that share a same feature space; and
wherein the ensemble query comprises a concatenation of the projected queries.

### Claim 3 (depends on 1)

The method of claim 1, wherein the prediction model comprises the transformer decoder and a prediction network that generates the predicted value.

### Claim 4 (depends on 3)

The method of claim 3, wherein the generating of the predicted value of the input data item comprises:
obtaining output embedding data by applying the ensemble query to the transformer decoder; and
obtaining the predicted value of the input data item by applying the output embedding data to the prediction network.

### Claim 5 (depends on 1)

The method of claim 1, wherein
the input data item comprises an image or a point cloud, and
the predicted value of the input data item comprises a bounding box of an object detected in the input data item or class information of the object.

### Claim 6 (depends on 5)

The method of claim 5, wherein the prediction model comprises:
a network configured for bounding box regression for object detection and is configured for a class estimation of an object corresponding to a bounding box.

### Claim 7 (depends on 1)

The method of claim 1, wherein the prediction model comprises:
a neural network trained based on a loss function related to a difference between the predicted value of the input data item and ground truth data of the input data item.

### Claim 8 (depends on 2)

The method of claim 2, wherein the projection networks and the prediction model comprise:
a neural network trained based on a loss function related to a difference between the predicted value of the input data item and ground truth data of the input data item.

### Claim 9 (depends on 2)

The method of claim 2, wherein the queries have different dimensions and the ensemble query is based on respective transformations of the queries that have a same dimension.

### Claim 10

A method of training an ensemble model based on feature-level consolidation, the method comprising:
obtaining queries by inputting a same training data item to respective transformer models, the transformer models generating respective queries from the training data item;
obtaining an ensemble query corresponding to the plurality of queries;
obtaining an estimated value of the training data item by applying the ensemble query to a prediction model comprising a transformer decoder; and
training the prediction model based on a loss function related to a difference between the estimated value of the training data item and ground truth data of the training data item.

### Claim 11 (depends on 10)

The training method of claim 10, wherein the obtaining of the ensemble query comprises:
obtaining projected queries corresponding to the queries based on respective projection networks that embed the queries into a same feature space; and
obtaining the ensemble query by concatenating the projected queries.

### Claim 12 (depends on 11)

The training method of claim 11, wherein the training of the prediction model comprises:
training the prediction model and the projection network based on the loss function.

### Claim 13 (depends on 10)

The training method of claim 10, wherein
the training data item comprises an image or a point cloud,
the estimated value of the training data item comprises a bounding box of an object detected in the input data item and a classification of the object, and
the prediction model comprises a network that is configured for bounding box regression for object detection and classification in the training data item.

### Claim 14 (depends on 10)

The training method of claim 10, wherein the obtaining of the estimated value of the training data item comprises:
obtaining output embedding data by applying the ensemble query to the transformer decoder of the prediction model; and
obtaining an estimated value of the training data item by applying the output embedding data to a prediction network of the prediction model, the prediction model inferring the estimated value of the training data item from the output embedding data.

### Claim 15 (depends on 1)

A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1.

### Claim 16

An apparatus comprising one or more processors configured to:
generate, by transformer-based models, respective queries corresponding to an input data item inputted to the transformer-based models;
obtain an ensemble query corresponding to the queries; and
obtain a predicted value of the input data item by applying the ensemble query to a prediction model comprising a transformer decoder.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein the one or more processors are further configured to, in obtaining the ensemble query:
obtain projected queries respectively corresponding to the queries, wherein the projected queries are obtained based on a projection network that projects the queries into the projected queries which are in a same feature space; and
wherein the ensemble query comprises a concatenation of the projected queries.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the projection network and the prediction model comprise:
a neural network trained based on a loss function related to a difference between the estimated value of the input data item and ground truth data of the input data item.

### Claim 19 (depends on 17)

The apparatus of claim 17, wherein the one or more processors are further configured to:
train the projection network and the prediction model based on a loss function related to a difference between the estimated value of the input data item and ground truth data of the input data item.

### Claim 20 (depends on 16)

The apparatus of claim 16, wherein
the input data item comprises an image and a point cloud,
the predicted value of the input data item comprises a bounding box of an object detected in the input data item or a classification of the object.
