Abstract: A context-based inspection system is disclosed. The system may include an optical imaging sub-system. The system may further include one or more controllers communicatively coupled to the optical imaging system. The one or more controllers may be configured to: receive one or more reference images; receive one or more test images of a sample; generate one or more probabilistic context maps during inspection runtime using an unsupervised classifier; provide the generated one or more probabilistic context maps to a supervised classifier during the inspection runtime; and apply the supervised classifier to the received one or more test images to identify one or more DOIs on the sample.

Abstract: A context-based inspection system is disclosed. The system may include an optical imaging sub-system. The system may further include one or more controllers communicatively coupled to the optical imaging system. The one or more controllers may be configured to: receive one or more reference images; receive one or more test images of a sample; generate one or more probabilistic context maps during inspection runtime using an unsupervised classifier; provide the generated one or more probabilistic context maps to a supervised classifier during the inspection runtime; and apply the supervised classifier to the received one or more test images to identify one or more DOIs on the sample.

Abstract: Methods and systems for accelerated training of a machine learning based model for semiconductor applications are provided. One method for training a machine learning based model includes acquiring information for non-nominal instances of specimen(s) on which a process is performed. The machine learning based model is configured for performing simulation(s) for the specimens. The machine learning based model is trained with only information for nominal instances of additional specimen(s). The method also includes re-training the machine learning based model with the information for the non-nominal instances of the specimen(s) thereby performing transfer learning of the information for the non-nominal instances of the specimen(s) to the machine learning based model.

Abstract: Methods and systems for training a neural network for defect detection in low resolution images are provided. One system includes an inspection tool that includes high and low resolution imaging subsystems and one or more components that include a high resolution neural network and a low resolution neural network. Computer subsystem(s) of the system are configured for generating a training set of defect images. At least one of the defect images is generated synthetically by the high resolution neural network using an image generated by the high resolution imaging subsystem. The computer subsystem(s) are also configured for training the low resolution neural network using the training set of defect images as input. In addition, the computer subsystem(s) are configured for detecting defects on another specimen by inputting the images generated for the other specimen by the low resolution imaging subsystem into the trained low resolution neural network.

Abstract: A defect detection method includes acquiring a reference image; selecting a target region of the reference image; identifying, based on a matching metric, one or more comparative regions of the reference image corresponding to the target region; acquiring a test image; masking the test image with the target region of the reference image and the one or more comparative regions of the reference image; defining a defect threshold for the target region in the test image based on the one or more comparative regions in the test image; and determining whether the target region of the test image contains a defect based on the defect threshold.

Abstract: Methods and systems for training a neural network for defect detection in low resolution images are provided. One system includes an inspection tool that includes high and low resolution imaging subsystems and one or more components that include a high resolution neural network and a low resolution neural network. Computer subsystem(s) of the system are configured for generating a training set of defect images. At least one of the defect images is generated synthetically by the high resolution neural network using an image generated by the high resolution imaging subsystem. The computer subsystem(s) are also configured for training the low resolution neural network using the training set of defect images as input. In addition, the computer subsystem(s) are configured for detecting defects on another specimen by inputting the images generated for the other specimen by the low resolution imaging subsystem into the trained low resolution neural network.

Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes a storage medium configured for storing images for a physical version of a specimen generated by an inspection system. At least two dies are formed on the specimen with different values of one or more parameters of a fabrication process performed on the specimen. The system also includes computer subsystem(s) configured for comparing portions of the stored images generated at locations on the specimen at which patterns having the same as-designed characteristics are formed with at least two of the different values. The portions of the stored images that are compared are not constrained by locations of the dies on the specimen, locations of the patterns within the dies, or locations of the patterns on the specimen. The computer subsystem(s) are also configured for detecting defects at the locations based on results of the comparing.

Abstract: Methods and systems for detecting defects in patterns formed on a specimen are provided. One system includes one or more components executed by one or more computer subsystems, and the component(s) include first and second learning based models. The first learning based model generates simulated contours for the patterns based on a design for the specimen, and the simulated contours are expected contours of a defect free version of the patterns in images of the specimen generated by an imaging subsystem. The second learning based model is configured for generating actual contours for the patterns in at least one acquired image of the patterns formed on the specimen. The computer subsystem(s) are configured for comparing the actual contours to the simulated contours and detecting defects in the patterns formed on the specimen based on results of the comparing.

Abstract: Methods and systems for performing one or more functions for a specimen using output simulated for the specimen are provided. One system includes one or more computer subsystems configured for acquiring output generated for a specimen by one or more detectors included in a tool configured to perform a process on the specimen. The system also includes one or more components executed by the one or more computer subsystems. The one or more components include a learning based model configured for performing one or more first functions using the acquired output as input to thereby generate simulated output for the specimen. The one or more computer subsystems are also configured for performing one or more second functions for the specimen using the simulated output.

Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes a generative model. The generative model includes a non-linear network configured for mapping blocks of pixels of an input feature map volume into labels. The labels are indicative of one or more defect-related characteristics of the blocks. The system inputs a single test image into the generative model, which determines features of blocks of pixels in the single test image and determines labels for the blocks based on the mapping. The system detects defects on the specimen based on the determined labels.

Abstract: Methods and systems for detecting defects in patterns formed on a specimen are provided. One system includes one or more components executed by one or more computer subsystems, and the component(s) include first and second learning based models. The first learning based model generates simulated contours for the patterns based on a design for the specimen, and the simulated contours are expected contours of a defect free version of the patterns in images of the specimen generated by an imaging subsystem. The second learning based model is configured for generating actual contours for the patterns in at least one acquired image of the patterns formed on the specimen. The computer subsystem(s) are configured for comparing the actual contours to the simulated contours and detecting defects in the patterns formed on the specimen based on results of the comparing.

Abstract: Methods and systems for generating simulated output for a specimen are provided. One method includes acquiring information for a specimen with one or more computer systems. The information includes at least one of an actual optical image of the specimen, an actual electron beam image of the specimen, and design data for the specimen. The method also includes inputting the information for the specimen into a learning based model. The learning based model is included in one or more components executed by the one or more computer systems. The learning based model is configured for mapping a triangular relationship between optical images, electron beam images, and design data, and the learning based model applies the triangular relationship to the input to thereby generate simulated images for the specimen.

Abstract: Methods and systems for performing one or more functions for a specimen using output simulated for the specimen are provided. One system includes one or more computer subsystems configured for acquiring output generated for a specimen by one or more detectors included in a tool configured to perform a process on the specimen. The system also includes one or more components executed by the one or more computer subsystems. The one or more components include a learning based model configured for performing one or more first functions using the acquired output as input to thereby generate simulated output for the specimen. The one or more computer subsystems are also configured for performing one or more second functions for the specimen using the simulated output.

Abstract: Methods and systems for generating simulated output for a specimen are provided. One method includes acquiring information for a specimen with one or more computer systems. The information includes at least one of an actual optical image of the specimen, an actual electron beam image of the specimen, and design data for the specimen. The method also includes inputting the information for the specimen into a learning based model. The learning based model is included in one or more components executed by the one or more computer systems. The learning based model is configured for mapping a triangular relationship between optical images, electron beam images, and design data, and the learning based model applies the triangular relationship to the input to thereby generate simulated images for the specimen.

Abstract: Methods and systems for accelerated training of a machine learning based model for semiconductor applications are provided. One method for training a machine learning based model includes acquiring information for non-nominal instances of specimen(s) on which a process is performed. The machine learning based model is configured for performing simulation(s) for the specimens. The machine learning based model is trained with only information for nominal instances of additional specimen(s). The method also includes re-training the machine learning based model with the information for the non-nominal instances of the specimen(s) thereby performing transfer learning of the information for the non-nominal instances of the specimen(s) to the machine learning based model.

Abstract: A defect detection method includes acquiring a reference image; selecting a target region of the reference image; identifying, based on a matching metric, one or more comparative regions of the reference image corresponding to the target region; acquiring a test image; masking the test image with the target region of the reference image and the one or more comparative regions of the reference image; defining a defect threshold for the target region in the test image based on the one or more comparative regions in the test image; and determining whether the target region of the test image contains a defect based on the defect threshold.

Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes a generative model. The generative model includes a non-linear network configured for mapping blocks of pixels of an input feature map volume into labels. The labels are indicative of one or more defect-related characteristics of the blocks. The system inputs a single test image into the generative model, which determines features of blocks of pixels in the single test image and determines labels for the blocks based on the mapping. The system detects defects on the specimen based on the determined labels.

Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes a storage medium configured for storing images for a physical version of a specimen generated by an inspection system. At least two dies are formed on the specimen with different values of one or more parameters of a fabrication process performed on the specimen. The system also includes computer subsystem(s) configured for comparing portions of the stored images generated at locations on the specimen at which patterns having the same as-designed characteristics are formed with at least two of the different values. The portions of the stored images that are compared are not constrained by locations of the dies on the specimen, locations of the patterns within the dies, or locations of the patterns on the specimen. The computer subsystem(s) are also configured for detecting defects at the locations based on results of the comparing.

Abstract: Methods and systems for detecting defects on a wafer are provided. One method includes creating a searchable database for a design for a wafer, which includes assigning values to different portions of the design based on patterns in the different portions of the design and storing the assigned values in the searchable database. Different portions of the design having substantially the same patterns are assigned the same values in the searchable database. The searchable database is configured such that searching of the database can be synchronized with generation of output for the wafer by one or more detectors of a wafer inspection system. Therefore, as the wafer is being scanned, design information for the output can be determined as fast as the output is generated, which enables multiple, desirable design based inspection capabilities.

Abstract: Methods and systems for detecting defects on a wafer are provided. One method includes creating a searchable database for a design for a wafer, which includes assigning values to different portions of the design based on patterns in the different portions of the design and storing the assigned values in the searchable database. Different portions of the design having substantially the same patterns are assigned the same values in the searchable database. The searchable database is configured such that searching of the database can be synchronized with generation of output for the wafer by one or more detectors of a wafer inspection system. Therefore, as the wafer is being scanned, design information for the output can be determined as fast as the output is generated, which enables multiple, desirable design based inspection capabilities.