# US 2026/0073657 A1 · Systems and methods for segmentation using retrieval augmentation

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

- Number: US 2026/0073657 A1
- Document ID: US20260073657A1
- Status: Published application
- Kind: A1
- Application number: 19/271,666
- Filed: 2025-07-16
- Published: 2026-03-12
- Earliest claimed: 2024-09-10
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Mostafa El-Khamy; Qingfeng Liu; Nafis Sadeq
- Web page: https://patentgrep.com/patent/US20260073657A1

## CPC

- G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06F 16/535: Filtering based on additional data, e.g. user or group profiles
- G06F 16/56: having vectorial format
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 10/764: using classification, e.g. of video objects
- 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)

## Abstract

A system and a method are disclosed for classifying features from an input image. The method includes generating, by a processing circuit, a segment feature from a first input image, the segment feature corresponding to a group of pixels associated with an object represented in the first input image, and being an out-of-vocabulary segment feature; performing, by the processing circuit, a retrieval of a first feature vector, corresponding to the segment feature, from a database of feature vectors, the first feature vector representing an object-specific segmentation mask; and generating, by the processing circuit, an output segmentation mask based on the first feature vector.

## Claims

### Claim 1

A method for classifying features from input images, the method comprising:
generating, by a processing circuit, a segment feature from a first input image, the segment feature corresponding to a group of pixels associated with an object represented in the first input image, and being an out-of-vocabulary segment feature;
performing, by the processing circuit, a retrieval of a first feature vector, corresponding to the segment feature, from a database of feature vectors, the first feature vector representing an object-specific segmentation mask; and
generating, by the processing circuit, an output segmentation mask based on the first feature vector.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
generating a first classification score for the segment feature based on an output of a CLIP text encoder;
generating a second classification score for the first feature vector based on a similarity between the segment feature and the first feature vector; and
determining a final segmentation score based on the first classification score and the second classification score,
wherein the output segmentation mask is generated based on the final segmentation score.

### Claim 3 (depends on 1)

The method of claim 1, further comprising generating the segment feature by:
sending input image data from the first input image to an object detector; and
sending an output of the object detector to a segmentation model.

### Claim 4 (depends on 1)

The method of claim 1, further comprising generating the segment feature based on sending a dense feature from the first input image to a pixel decoder.

### Claim 5 (depends on 1)

The method of claim 1, further comprising generating the database of feature vectors by:
sending a dense feature from a second input image to an object detector;
sending an output of the object detector to a segmentation model to generate a mask proposal;
generating the object-specific segmentation mask based on the mask proposal; and
generating the first feature vector based on the object-specific segmentation mask.

### Claim 6 (depends on 1)

The method of claim 1, wherein:
the first feature vector is generated based on segment-to-text embedding; and
the segment feature is generated based on segment-to-vision embedding.

### Claim 7 (depends on 1)

The method of claim 1, wherein the performing of the retrieval comprises performing a nearest-neighbor search based on the segment feature.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
performing a search in the database of feature vectors based on a second segment feature; and
based on the search resulting in a miss, retrieving a second feature vector from a secondary dataset.

### Claim 9

A system comprising:
a processing circuit; and
a memory storing instructions that, based on being executed by the processing circuit, cause the processing circuit to perform:
generating a segment feature from a first input image, the segment feature corresponding to a group of pixels associated with an object represented in the first input image, and being an out-of-vocabulary segment feature;
a retrieval of a first feature vector, corresponding to the segment feature, from a database of feature vectors, the first feature vector representing an object-specific segmentation mask; and
generating an output segmentation mask based on the first feature vector.

### Claim 10 (depends on 9)

The system of claim 9, wherein the instructions, based on being executed by the processing circuit, cause the processing circuit to perform:
generating a first classification score for the segment feature based on an output of a CLIP text encoder;
generating a second classification score for the first feature vector based on a similarity between the segment feature and the first feature vector; and
determining a final segmentation score based on the first classification score and the second classification score,
wherein the output segmentation mask is generated based on the final segmentation score.

### Claim 11 (depends on 9)

The system of claim 9, wherein the instructions, based on being executed by the processing circuit, cause the processing circuit to perform:
generating the segment feature by:
sending input-image data from the first input image to an object detector; and
sending an output of the object detector to a segmentation model.

### Claim 12 (depends on 9)

The system of claim 9, wherein the instructions, based on being executed by the processing circuit, cause the processing circuit to perform:
generating the segment feature based on sending a dense feature from the first input image to a pixel decoder.

### Claim 13 (depends on 9)

The system of claim 9, wherein the instructions, based on being executed by the processing circuit, cause the processing circuit to perform:
generating the database of feature vectors by:
sending a dense feature from a second input image to an object detector;
sending an output of the object detector to a segmentation model to generate a mask proposal;
generating the object-specific segmentation mask based on the mask proposal; and
generating the first feature vector based on the object-specific segmentation mask.

### Claim 14 (depends on 9)

The system of claim 9, wherein:
the first feature vector is generated based on segment-to-text embedding; and
the segment feature is generated based on segment-to-vision embedding.

### Claim 15 (depends on 9)

The system of claim 9, wherein the performing of the retrieval comprises performing a nearest-neighbor search based on the segment feature.

### Claim 16 (depends on 9)

The system of claim 9, wherein the instructions, based on being executed by the processing circuit, cause the processing circuit to perform:
a search in the database of feature vectors based on a second segment feature; and
based on the search resulting in a miss, retrieving a second feature vector from a secondary dataset.

### Claim 17

A device comprising:
an image sensor configured to generate an input image; and
a means for processing, the means for processing being configured to perform a method for classifying features from the input image, the method comprising:
generating, by the means for processing, a segment feature from a first input image, the segment feature corresponding to a group of pixels associated with an object represented in the first input image, and being an out-of-vocabulary segment feature;
performing, by the means for processing, a retrieval of a first feature vector, corresponding to the segment feature, from a database of feature vectors, the first feature vector representing an object-specific segmentation mask; and
generating, by the means for processing, an output segmentation mask based on the first feature vector.

### Claim 18 (depends on 17)

The device of claim 17, wherein the method further comprises:
generating a first classification score for the segment feature based on an output of a CLIP text encoder;
generating a second classification score for the first feature vector based on a similarity between the segment feature and the first feature vector; and
determining a final segmentation score based on the first classification score and the second classification score,
wherein the output segmentation mask is generated based on the final segmentation score.

### Claim 19 (depends on 17)

The device of claim 17, wherein the method further comprises generating the segment feature by:
sending input-image data from the first input image to an object detector; and
sending an output of the object detector to a segmentation model.

### Claim 20 (depends on 17)

The device of claim 17, wherein the method further comprises generating the segment feature based on sending a dense feature from the first input image to a pixel decoder.
