# US 2025/0155378 A1 · Computer implemented method for defect detection in an imaging dataset of an object comprising integrated circuit patterns using machine learning models with attention mechanism

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

- Number: US 2025/0155378 A1
- Document ID: US20250155378A1
- Status: Published application
- Kind: A1
- Application number: 18/938,425
- Filed: 2024-11-06
- Published: 2025-05-15
- Earliest claimed: 2023-11-10
- Applicants: Carl Zeiss SMT GmbH
- Inventors: Alexander Freytag; Bjoern Froehlich; Bjoern Barz; Bjoern Brauer
- Web page: https://patentgrep.com/patent/US20250155378A1

## CPC

- G01N 21/8851: {Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges (G01N21/8806 and G01N21/93 - G01N21/95692 take precedence; optical measurement of dimensions G01B11/00; optical scanning G02B26/10; image transformation G06T3/00; computerised image enhancement G06T5/00; image processing per se for flaw detection G06T7/0002)}
- G01N 21/9501: {Semiconductor wafers (manufacturing processes per se of semiconductor devices implementing a measuring step H10P74/20)}
- G06T 7/0004: {Industrial image inspection}
- G06T 7/001: {using an image reference approach}
- H10P 74/203: {Structural properties, e.g. testing or measuring thicknesses, line widths, warpage, bond strengths or physical defects}
- G01N 2021/8887: {based on image processing techniques}
- G06T 2207/10061: from scanning electron microscope
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30148: Semiconductor; IC; Wafer
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10

## Abstract

The invention relates to a computer implemented method for defect detection comprising: obtaining an imaging dataset and a reference dataset of an object comprising integrated circuit patterns; and detecting defects in the imaging dataset using the imaging dataset and the reference dataset, wherein a machine learning model for defect highlighting is applied to the imaging dataset as input and generates a highlighted defect dataset as output, and wherein the machine learning model for defect highlighting comprises at least one attention mechanism. The invention also relates to computer programs, computer-readable media and corresponding systems.

## Claims

### Claim 1

A computer implemented method for defect detection comprising:
obtaining an imaging dataset and a reference dataset of an object comprising integrated circuit patterns,
detecting defects in the imaging dataset using the imaging dataset and the reference dataset, wherein a machine learning model for defect highlighting is applied to the imaging dataset as input and generates a highlighted defect dataset as output, and wherein the machine learning model for defect highlighting comprises at least one attention mechanism.

### Claim 2 (depends on 1)

The method of claim 1, wherein the reference dataset is generated using a further machine learning model.

### Claim 3 (depends on 2)

The method of claim 2, wherein the further machine learning model comprises at least one attention mechanism.

### Claim 4 (depends on 1)

The method of claim 1, wherein defects are detected by comparing the highlighted defect dataset to the reference dataset.

### Claim 5 (depends on 1)

The method of claim 1, wherein the machine learning model for defect highlighting uses the reference dataset as additional input.

### Claim 6 (depends on 5)

The method of claim 5, wherein the machine learning model for defect highlighting maps the imaging dataset and the reference dataset to the highlighted defect dataset.

### Claim 7 (depends on 5)

The method of claim 5, wherein the machine learning model for defect highlighting reconstructs the imaging dataset and the reference dataset, and wherein the highlighted defect dataset is obtained by comparing the reconstruction of the imaging dataset to the reconstruction of the reference dataset.

### Claim 8 (depends on 1)

The method of claim 1, wherein the machine learning model for defect highlighting computes a reconstruction of the input including the defects.

### Claim 9 (depends on 8)

The method of claim 8, wherein the machine learning model for defect highlighting reconstructs defective regions in the input with a higher accuracy than defect-free regions.

### Claim 10 (depends on 8)

The method of claim 8, wherein the machine learning model for defect highlighting amplifies the defects in the input.

### Claim 11 (depends on 1)

The method of claim 1, wherein the machine learning model for defect highlighting comprises a convolutional neural network that contains at least one attention mechanism.

### Claim 12 (depends on 11)

The method of claim 11, wherein the convolution neural network comprises an encoder—decoder architecture.

### Claim 13 (depends on 11)

The method of claim 11, wherein the convolutional neural network is configured as a U-Net.

### Claim 14 (depends on 1)

The method of claim 1, wherein the machine learning model for defect highlighting comprises a Vision Transformer.

### Claim 15 (depends on 14)

The method of claim 14, wherein the Vision Transformer is pre-trained using masked autoencoding.

### Claim 16 (depends on 14)

The method of claim 14, wherein the detection of defects comprises:
partitioning the imaging dataset of the object comprising integrated circuit patterns into a set of patches;
iteratively masking one or more of the patches of the imaging dataset and applying the Vision Transformer machine learning model to reconstruct the one or more masked patches; and
obtaining a highlighted defect dataset in the form of a reconstructed imaging dataset from the one or more reconstructed masked patches.

### Claim 17 (depends on 1)

The method of claim 1, wherein the input to the machine learning model additionally comprises one or more meta tokens representing meta information concerning the imaging dataset and/or the imaging device used to obtain the imaging dataset.

### Claim 18 (depends on 1)

A computer implemented method for training a machine learning model for defect highlighting according to claim 1, the method comprising:
providing training images of objects comprising integrated circuit patterns; and
training the machine learning model for defect highlighting using the provided training images by minimizing a loss function configured for highlighting defects.

### Claim 19 (depends on 14)

A computer implemented method for training a Vision Transformer machine learning model according to claim 14, the method comprising:
providing training images of objects comprising integrated circuit patterns;
partitioning each training image into patches; and
training the Vision Transformer machine learning model by iteratively presenting one or more training images to the Vision Transformer machine learning model, wherein one or more patches of each training image are masked, and modifying the parameters of the Vision Transformer machine learning model by minimizing a loss function configured for highlighting defects.

### Claim 20 (depends on 19)

The method of claim 19, wherein the patches are defined using meta information from the group comprising critical dimension, relevant and/or irrelevant locations, structures or structure types, design information of the object comprising integrated circuit patterns.

### Claim 21 (depends on 19)

The method of claim 19, wherein the machine learning model for defect highlighting computes a reconstruction of the imaging dataset, and wherein the loss function comprises a deviation of the reconstruction from the imaging dataset.

### Claim 22 (depends on 19)

The method of claim 19, wherein the training images comprise annotated defects.

### Claim 23 (depends on 21)

The method of claim 21, wherein the training images comprise annotated defects, and the loss function applies a higher penalty to deviations of the reconstruction from the imaging dataset within defective regions than within defect-free regions.

### Claim 24 (depends on 22)

The method of claim 22, wherein the loss function is configured to highlight features within the defects.

### Claim 25 (depends on 22)

The method of claim 22, wherein the loss function is configured to modify properties of the imaging dataset within defective regions.

### Claim 26 (depends on 22)

The method of claim 22, wherein the majority of defects in the training images are weakly annotated.

### Claim 27 (depends on 1)

A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out a method for defect detection of claim 1.

### Claim 28 (depends on 1)

A computer-readable medium, on which a computer program executable by a computing device is stored, the computer program comprising code for executing a method for defect detection of claim 1.

### Claim 29 (depends on 1)

A system for defect detection comprises:
an imaging device configured to provide an imaging dataset of an object comprising integrated circuit patterns;
one or more processing devices; and
one or more machine-readable hardware storage devices comprising instructions that are executable by one or more processing devices to apply a method for defect detection according to claim 1 to the imaging dataset of the object comprising integrated circuit patterns.
