Search

US-20260127730-A1 - Generative Approach for Images Towards Advanced Node Defect Inspection

US20260127730A1US 20260127730 A1US20260127730 A1US 20260127730A1US-20260127730-A1

Abstract

The present disclosure describes a generative approach for better semiconductor device defect detection. An example method includes providing an original image set, wherein the original image set comprises a plurality of full-size images. The method also includes extracting one or more patches from the plurality of images, wherein each patch of the one or more patches includes at least a portion of a semiconductor device feature. The method yet further includes classifying each patch as either defect-present or defect-free so as to provide labelled patches that include the semiconductor device feature. The method additionally includes training a denoising diffusion probabilistic model (DDPM) based on the labelled patches and generating, using the trained DDPM, a plurality of synthetic images.

Inventors

  • Bappaditya Dey
  • Victor M. Blanco
  • Vic De Ridder

Assignees

  • IMEC VZW

Dates

Publication Date
20260507
Application Date
20241104

Claims (20)

  1. 1 . A method comprising: providing an original image set, wherein the original image set comprises a plurality of full-size images; extracting one or more patches from the plurality of images, wherein each patch of the one or more patches includes at least a portion of a semiconductor device feature; classifying each patch as either defect-present or defect-free so as to provide labelled patches that include the semiconductor device feature; training a denoising diffusion probabilistic model (DDPM) based on the labelled patches; and generating, using the trained DDPM, a plurality of synthetic images.
  2. 2 . The method of claim 1 , further comprising: if a respective patch is classified as having a defect, classifying the defect as having a defect type from among a set of possible defect types.
  3. 3 . The method of claim 1 , wherein the full-size images have an image size of 1024×1024 pixels or larger.
  4. 4 . The method of claim 1 , wherein providing the original image set comprises providing a plurality of images from at least one of: an LS-ADI real test dataset, an LS-AEI real test dataset, or a HEXCH-DSA real test dataset.
  5. 5 . The method of claim 1 , wherein extracting one or more patches comprises extracting portions of the images having a default image size of 128×128 pixels, 256×256 pixels, or 512×512 pixels.
  6. 6 . The method of claim 1 , wherein training the DDPM comprises using a cosine noise schedule and between 100 to 10,000 sample steps.
  7. 7 . The method of claim 1 , wherein training the DDPM comprises using a learning rate of between 0.001 and 0.00001 until convergence.
  8. 8 . The method of claim 1 , wherein generating the plurality of synthetic images comprises generating a plurality of full-size synthetic images, wherein each synthetic image of the plurality of synthetic images comprises at least one defect from a corresponding defect type.
  9. 9 . The method of claim 1 , wherein generating each synthetic image of the plurality of synthetic images comprises: selecting a desired defect type; generating an initial patch; and inpainting a portion of the initial patch with a simulated defect of the desired defect type.
  10. 10 . The method of claim 9 , wherein generating each synthetic image of the plurality of synthetic images further comprises: incrementally repeating the inpainting step with subsequent patches based on output from the DDPM so as to increase the size of the patch until a full-size output image is provided.
  11. 11 . The method of claim 1 , wherein generating the plurality of synthetic images is performed without prior knowledge of SEM tool imaging conditions.
  12. 12 . The method of claim 1 , further comprising: training a defect detector with the plurality of synthetic images to detect defects from one or more defect types.
  13. 13 . The method of claim 12 , wherein training the defect detector comprises training an object detection model that utilizes a cross stage partial (CSP) network.
  14. 14 . The method of claim 12 , further comprising: determining, using the trained defect detector, whether a defect is present in the plurality of synthetic images; and classifying each synthetic image of the plurality of synthetic images as either defect-present or defect-free so as to obtain labelled synthetic images.
  15. 15 . The method of claim 12 , further comprising: determining, using the trained defect detector, whether a defect is present in a plurality of real SEM images; and classifying each real image of the plurality of real images as either defect-present or defect-free so as to obtain labelled real images.
  16. 16 . The method of claim 12 , further comprising: determining, using the trained defect detector, whether a defect is present in the plurality of synthetic images; classifying each synthetic image of the plurality of synthetic images as either defect-present or defect-free so as to obtain labelled synthetic images; determining, using the trained defect detector, whether a defect is present in a plurality of real SEM images; classifying each real image of the plurality of real images as either defect-present or defect-free so as to obtain labelled real images; and determining, based on the labelled synthetic images and the labelled real images, performance metrics for detecting one or more selected defects and defect types within the respective labelled synthetic images and the labelled real images.
  17. 17 . A method for training a defect detector, the method comprising: generating, using a trained denoising diffusion probabilistic model (DDPM), a plurality of synthetic images, wherein the DDPM was initially trained on a plurality of patches extracted from full-size images; and training a defect detector with the plurality of synthetic images so as to detect defects within input images.
  18. 18 . The method of claim 17 , wherein training the defect detector comprises training an object detection model that utilizes a cross stage partial (CSP) network.
  19. 19 . A method for detecting defects in semiconductor devices, the method comprising: receiving at least one full-size image; determining, using a trained defect detector, whether a defect is present in the image; and if it is determined that a defect is present in the image, classifying the defect as having a defect type from among a set of possible defect types.
  20. 20 . The method of claim 19 , further comprising: determining, based on the plurality of synthetic images and the at least one SEM image, performance metrics for successfully detecting one or more selected defects and defect types within the at least one image.

Description

BACKGROUND Unless otherwise indicated herein, the materials described in this section are not prior art to the claims in this application and are not admitted to be prior art by inclusion in this section. As Moore's Law drives the semiconductor industry towards achieving ever-smaller feature sizes (≤10 nm) and increased transistor density, the traditional methods of patterning face challenges. New approaches, including emerging lithography technologies like Extreme-Ultra-Violet-Lithography (EUVL) (≤7 nm), high-NA EUVL (≤2 nm), and other alternatives, are being developed to keep pace with Moore's Law and maintain the relentless pursuit of smaller feature sizes. The escalating complexity of semiconductor devices necessitates a corresponding elevation in process control. This entails the integration of precise metrology, sophisticated data analysis, and cutting-edge defect inspection methodologies. The prevailing state-of-the-art (SOTA) defect detection tools, whether optical or e-beam based, exhibit specific limitations. These tools rely on rule-based techniques for defect classification and detection, which introduces constraints in their adaptability and effectiveness. The use of rule-based approaches implies that these tools are programmed with predefined criteria to identify and classify defects. While this methodology is effective for well-understood and predictable defect patterns, it becomes increasingly challenging when dealing with complex, evolving, or stochastic defects, specifically in the presence of reduced signal-to-noise ratio (SNR) and image contrast. Due to the inadequacy of rule-based methods at advanced nodes, DL-based object detectors have emerged as the state-of-the-art for stochastic defect inspection. However, the acquisition of a relevant stochastic defect dataset for training ML models faces considerable challenges within the semiconductor manufacturing domain. Not only is such a dataset rare and inherently noisy, but its acquisition is also a costly endeavor. The rarity of stochastic defect instances makes it challenging to compile a comprehensive dataset that accurately represents the diverse range of stochastic defects encountered in real-world semiconductor manufacturing processes. Additionally, two significant bottlenecks further complicate the use of stochastic defect datasets in semiconductor manufacturing defect detection: (a) class imbalance, which arises when certain defect types are underrepresented or occur infrequently in the dataset, leading to a skewed distribution. This imbalance can compromise the model's ability to generalize and accurately detect defects across all classes. (b) insufficient dataset size, as a limited amount of data may not adequately capture the variability and complexity of stochastic defects. The inherent diversity of semiconductor manufacturing processes demands large and representative datasets to ensure the robust training of machine learning models. Addressing these challenges requires innovative approaches to dataset acquisition, including strategic data augmentation techniques to enhance dataset diversity. Collaboration within the industry and the development of shared datasets could also contribute to mitigating the issues associated with rare, noisy, and expensive stochastic defect datasets. Overcoming these challenges is pivotal for advancing the capabilities of machine learning models in semiconductor manufacturing defect detection. SUMMARY Example embodiments utilize Denoising Diffusion Probabilistic Models (DDPM) to generate realistic semiconductor wafer images, thereby increasing defect inspection training data and improving defect inspection performance. Multiple aspects are presented: i) a patch-based generative framework is proposed that utilizes DDPM to generate SEM images that include intended defect classes with randomly variable instances, aiming to address class-imbalance and data insufficiency bottlenecks. This approach leads to an enhancement in defect detection performance, particularly in terms of precision and recall. ii) synthetic images are generated that closely resemble real images, preserving actual defect characteristics without the need for prior knowledge of imaging settings under Best-Known-Methods. iii) a defect detector has been developed and trained on a generated defect dataset, either independently or in combination with a limited real dataset, can achieve a similar or improved mAP on real wafer images during validation/testing compared to when trained exclusively on a real defect dataset. This trend was consistent across three different SEM datasets, validating the capability of DDPM to generate images with characteristics identical to real SEM images. Finally, iv) the systems and methods described herein demonstrate the capability to transfer defect types, critical dimensions, and imaging conditions from one specified CD/Pitch and metrology specifications to another CD/Pitch and metrology specifications.