# US 2026/0065154 A1 · Three-stage semi-supervised instance segmentation training method and system

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

- Number: US 2026/0065154 A1
- Document ID: US20260065154A1
- Status: Published application
- Kind: A1
- Application number: 19/264,828
- Filed: 2025-07-09
- Published: 2026-03-05
- Earliest claimed: 2024-09-04
- Assignees: Lite-On Technology Corporation
- Applicants: Lite-On Technology Corporation
- Inventors: Jiun-In Guo; Hua-Ren Liao; CHIH-YUAN CHUANG; JIUN-SHIUNG CHEN
- Web page: https://patentgrep.com/patent/US20260065154A1

## CPC

- G06N 20/00: Machine learning
- G06N 3/045: Combinations of networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A three-stage semi-supervised instance segmentation training method and a system. In a first stage, a teacher model and a student model are trained based on labeled data. In a second stage, the teacher model performs prediction on unlabeled data and generates pseudo labels according to a prediction result. The student model learns labeled data and unlabeled data based on the pseudo labels. A soft label filter is used to filter for obtaining high-quality pseudo labels, a positive sample loss function is used to eliminate a problem of incorrect model convergence due to the pseudo labels with incomplete information, and the parameters of the student model are updated via a backward propagation process. In a third stage, the parameters of the student model are transferred to the teacher model through an exponential moving average operation, so that the teacher model and the student model are under a same architecture.

## Claims

### Claim 1

A three-stage semi-supervised instance segmentation training method, comprising:
at a first stage, training a teacher model and a student model through labeled data for making the teacher model and the student model reach a stable state, wherein the teacher model and the student model are respectively trained by different qualities of data;
at a second stage, the teacher model performing prediction on unlabeled data, assigning pseudo labels to the unlabeled data according to a confidence with respect to a prediction result, providing the pseudo labels to the student model, making the student model learn the labeled data, and learning the unlabeled data based on the pseudo labels; and
at a third stage, updating parameters of the student model to the teacher model.

### Claim 2 (depends on 1)

The method according to claim 1, wherein, at the first stage and the second stage, according to a scaling training strategy, the teacher model learns high-resolution pictures so as to generate reliable pseudo labels.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the parameters of the student model are weights and an exponential moving average operation is incorporated to update the student model to be the teacher model through the weights.

### Claim 4 (depends on 1)

The method according to claim 1, wherein, at the second stage, the unlabeled data and the pseudo label form a training data used to train the student model, a positive sample loss function is performed to classify the data and calculate positive sample losses of the labeled data and the unlabeled data for eliminating a problem of incorrect model convergence due to the pseudo labels with incomplete information; and the student model is updated according to errors calculated from the positive sample losses through a backward propagation process.

### Claim 5 (depends on 1)

The method according to claim 1, wherein, at the second stage, a soft label filter is used to filter for obtaining high-quality pseudo labels.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the soft label filter employs a first threshold and a second threshold, by which a first weight is assigned to the data with the pseudo labels having confidences greater than the first threshold, a second weight is assigned to the data with the pseudo labels having confidences between the first threshold and the second threshold, and the data with the pseudo labels having confidences less than the second threshold is discarded.

### Claim 7 (depends on 6)

The method according to claim 6, wherein, at the first stage and the second stage, according to a scaling training strategy, the teacher model learns high-resolution pictures so as to generate reliable pseudo labels.

### Claim 8 (depends on 1)

The method according to claim 1, wherein asymmetric teacher-student model architecture allows the teacher model and the student model to have a same model type with different precisions, or different model types with different precisions.

### Claim 9 (depends on 8)

The method according to claim 8, wherein, at the first stage and the second stage, according to a scaling training strategy, the teacher model learns high-resolution pictures so as to generate reliable pseudo labels.

### Claim 10 (depends on 9)

The method according to claim 9, wherein, when using the unlabeled data to train the teacher model, a weak data augmented strategy is incorporated to learn images that are not substantially changed, and, when using the unlabeled data to train the student model, a strong data augmented strategy is incorporated to learn images that are significantly changed so as to make a final performance of the student model greater than the teacher model.

### Claim 11

A system operating a three-stage semi-supervised instance segmentation training method, comprising:
a computing device, using a computing circuit to perform the three-stage semi-supervised instance segmentation training method comprising:
at a first stage, training a teacher model and a student model through labeled data for making the teacher model and the student model reach a stable state, wherein the teacher model and the student model are respectively trained by different qualities of data;
at a second stage, the teacher model performing prediction on unlabeled data, assigning pseudo labels to the unlabeled data according to a confidence with respect to a prediction result, providing the pseudo labels to the student model, making the student model learn the labeled data, and learning the unlabeled data based on the pseudo labels; and
at a third stage, updating parameters of the student model to the teacher model.

### Claim 12 (depends on 11)

The system according to claim 11, wherein, at the first stage and the second stage, according to a scaling training strategy, the teacher model learns high-resolution pictures so as to generate reliable pseudo labels.

### Claim 13 (depends on 11)

The system according to claim 11, wherein the parameters of the student model are weights and an exponential moving average operation is incorporated to update the student model to be the teacher through the weights.

### Claim 14 (depends on 11)

The system according to claim 11, wherein a positive sample loss function is performed for classifying the data into the labeled data and the unlabeled data for calculating the positive sample losses so as to eliminate a problem of incorrect model convergence due to the pseudo labels with incomplete information.

### Claim 15 (depends on 11)

The system according to claim 11, wherein, at the second stage, a soft label filter is used to filter for obtaining high-quality pseudo labels.

### Claim 16 (depends on 15)

The system according to claim 15, wherein the soft label filter employs a first threshold and a second threshold, by which a first weight is assigned to the data with the pseudo labels having confidences greater than the first threshold, a second weight is assigned to the data with the pseudo labels having confidences between the first threshold and the second threshold, and the data with the pseudo labels having confidences less than the second threshold is discarded.

### Claim 17 (depends on 16)

The system according to claim 16, wherein, at the first stage and the second stage, according to a scaling training strategy, the teacher model learns high-resolution pictures so as to generate reliable pseudo labels.

### Claim 18 (depends on 11)

The system according to claim 11, wherein the system adopts asymmetric teacher-student model architecture that allows the teacher model and the student model to have a same model type with different precisions, or different model types with different precisions.

### Claim 19 (depends on 18)

The system according to claim 18, wherein, at the first stage and the second stage, according to a scaling training strategy, the teacher model learns high-resolution pictures so as to generate reliable pseudo labels.

### Claim 20 (depends on 19)

The system according to claim 19, wherein, when using the unlabeled data to train the teacher model, a weak data augmented strategy is incorporated to learn images that are not substantially changed, and, when using the unlabeled data to train the student model, a strong data augmented strategy is incorporated to learn images that are significantly changed so as to make a final performance of the student model greater than the teacher model.
