Mode selection and defect detection training

Patent metadata

Field	Value
Publication number	US-11769242-B2
Application number	US-202017128502-A
Country	US
Kind code	B2
Filing date	Dec 21, 2020
Priority date	May 21, 2020
Publication date	Sep 26, 2023
Grant date	Sep 26, 2023

Abstract

A system may be configured for joint defect discovery and optical mode selection. Defects are detected during a defect discovery step. The discovered defects are accumulated into a mode selection dataset. The mode selection dataset is used to perform mode selection to determine a mode combination. The mode combination may then be used to train the defect detection model. Additional defects may then be detected by the defect detection model. The additional defects may then be provided to the mode selection dataset, for further performing mode selection and training the defect detection model. One or more run-time modes may then be determined. The system may be configured for mode selection and defect detection at an image pixel level.

First claim

What is claimed:

1. A system comprising:
a controller communicatively coupled to an inspection sub-system, the inspection sub-system configured to image at least one sample while being configured with any of a plurality of candidate optical modes, the controller including one or more processors configured to execute program instructions causing the one or more processors to jointly perform optical mode selection and defect detection training by iteratively:
receiving defect data of at least one defect on at least a portion of the at least one sample;
receiving at least one image from the inspection sub-system and storing the at least one image in a dataset, wherein the at least one image is associated with the at least one defect detected on the at least the portion of the at least one sample by the inspection sub-system configured with a candidate optical mode of the plurality of candidate optical modes;
selecting one or more optical modes from the plurality of candidate optical modes by performing a mode selection model; and
training a defect detection model with images associated with the one or more selected optical modes;

wherein the one or more processors are further configured to determine at least one run-time optical mode from the plurality of candidate optical modes.

2. The system of claim 1 , wherein the mode selection model comprises:
a sparse vector, the sparse vector including a plurality of indices, each of the plurality of indices including a mode selection weight between zero and a first value.

3. The system of claim 2 , wherein the one or more optical modes selected by the mode selection model are selected by applying a threshold to the sparse vector.

4. The system of claim 2 , wherein the one or more optical modes selected by the mode selection model are selected by providing the plurality of indices to the defect detection model as a weighting vector.

5. The system of claim 1 , wherein the mode selection model comprises:
a random channel dropout vector, the random channel dropout vector including a plurality of indices, each of the plurality of indices including a mode selection weight of either zero or non-zero.

6. The system of claim 5 , wherein the plurality of indices are randomly set to either a zero or a non-zero value during each iteration.

7. The system of claim 6 , wherein the one or more optical modes of the dataset in which to train the defect detection model are determined by the plurality of indices having the non-zero value.

8. The system of claim 1 , wherein the mode selection model includes a model agnostic meta-learning algorithm.

9. The system of claim 1 , wherein the mode selection model comprises at least one of forward selection or backward selection algorithm.

10. The system of claim 1 , wherein determining the at least one run-time mode includes generating a ranking table, the ranking table including at least one of a signal to noise ratio, a receiver operating characteristic curve, a capture rate, a nuisance rate, or a computation cost.

11. The system of claim 1 , wherein the plurality of candidate optical modes are determined by dimension reduction, the dimension reduction including at least one of correlation analysis or principle component analysis.

12. The system of claim 1 , wherein each of the plurality of candidate optical modes includes a wavelength, a focal length, an aperture, and a bandwidth.

13. The system of claim 1 , wherein the defect detection model includes at least one of a deep generative model, a convolutional neural network, a generative adversarial network, a conditional generative adversarial network, a variational autoencoder, a representation learning network, or a transformer model.

14. The system of claim 1 , wherein the inspection sub-system includes a broadband plasma inspection tool.

15. The system of claim 1 , further comprising performing a defect inspection test.

16. The system of claim 15 , further comprising performing an inference using the defect detection model to evaluate at least one of a stability or a sensitivity of the defect detection model.

17. The system of claim 1 , wherein the inspection sub-system is configured to image the at least one sample while configured with the one or more optical modes selected from the plurality of candidate modes by the mode selection model, when the one or more optical modes do not include an associated image in the dataset.

18. A method for performing optical mode selection and defect detection training comprising:
receiving defect data of at least one defect on at least a portion of at least one sample;
receiving at least one image from an inspection sub-system and storing the at least one image in a dataset, wherein the at least one image is associated with the at least one defect detected on the at least the portion of the at least one sample by the inspection sub-system configured with a candidate optical mode of a plurality of candidate optical modes;
selecting one or more optical modes from the plurality of candidate optical modes by performing a mode selection model;
training a defect detection model with the images associated with the one or more optical modes selected by the mode selection model; and
performing a defect inspection test.

19. The method of claim 18 , wherein the mode selection model includes one or more of a random channel dropout vector, a sparse vector, a model-agnostic meta learning algorithm, a forward selection algorithm, or a backward selection algorithm.

20. A system comprising:
an inspection sub-system configured to image at least one sample while being configured with a plurality of candidate optical modes;
a controller communicatively coupled to the inspection sub-system, the controller including one or more processors configured to execute program instructions causing the one or more processors to jointly perform optical mode selection and defect detection training by iteratively:
receiving defect data of at least one defect on at least a portion of the at least one sample;
receiving at least one image from the inspection sub-system and storing the at least one image in a dataset, wherein the at least one image is associated with the at least one defect detected on the at least the portion of the at least one sample by the inspection sub-system configured with a candidate optical mode of the plurality of candidate optical modes;
selecting one or more optical modes from the plurality of candidate optical modes by performing a mode selection model; and
training a defect detection model with images associated with the one or more selected optical modes;

wherein the one or more processors are further configured to determine at least one run-time optical mode from the plurality of candidate optical modes.

Assignees

• Kla Corp

Inventors

• Zhang Jing
• Dong Yujie
• Bhatia Vishank
• Mcbride Patrick
• Bhaskar Kris
• Duffy Brian

Classifications

• G06T7/0004 Primary

  Industrial image inspection · CPC title

• G01N21/9501 Primary

  Semiconductor wafers (manufacturing processes per se of semiconductor devices implementing a measuring step H10P74/20) · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/30148

  Semiconductor; IC; Wafer · CPC title