Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics

• URL: http://arxiv.org/abs/2504.10021v1
• Date: Mon, 14 Apr 2025 09:25:50 GMT
• Title: Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics
• Authors: Nikolai Röhrich, Alwin Hoffmann, Richard Nordsieck, Emilio Zarbali, Alireza Javanmardi,
• Abstract summary: We propose a vision transformer (ViT) pre-training framework for defect detection in microelectronics based on masked autoencoders (MAE)<n>We perform pre-training and defect detection using a dataset of less than 10.000 scanning acoustic microscopy (SAM) images labelled using transient thermal analysis (TTA)<n>Our approach leads to substantial performance gains compared to a) supervised ViT, b) ViT pre-trained on natural image datasets, and c) state-of-the-art CNN-based defect detection models used in the literature.
• Score: 0.7456526005219319
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Whereas in general computer vision, transformer-based architectures have quickly become the gold standard, microelectronics defect detection still heavily relies on convolutional neural networks (CNNs). We hypothesize that this is due to the fact that a) transformers have an increased need for data and b) labelled image generation procedures for microelectronics are costly, and labelled data is therefore sparse. Whereas in other domains, pre-training on large natural image datasets can mitigate this problem, in microelectronics transfer learning is hindered due to the dissimilarity of domain data and natural images. Therefore, we evaluate self pre-training, where models are pre-trained on the target dataset, rather than another dataset. We propose a vision transformer (ViT) pre-training framework for defect detection in microelectronics based on masked autoencoders (MAE). In MAE, a large share of image patches is masked and reconstructed by the model during pre-training. We perform pre-training and defect detection using a dataset of less than 10.000 scanning acoustic microscopy (SAM) images labelled using transient thermal analysis (TTA). Our experimental results show that our approach leads to substantial performance gains compared to a) supervised ViT, b) ViT pre-trained on natural image datasets, and c) state-of-the-art CNN-based defect detection models used in the literature. Additionally, interpretability analysis reveals that our self pre-trained models, in comparison to ViT baselines, correctly focus on defect-relevant features such as cracks in the solder material. This demonstrates that our approach yields fault-specific feature representations, making our self pre-trained models viable for real-world defect detection in microelectronics.

Related papers

• MaskTerial: A Foundation Model for Automated 2D Material Flake Detection [48.73213960205105]
  We present a deep learning model, called MaskTerial, that uses an instance segmentation network to reliably identify 2D material flakes.<n>The model is extensively pre-trained using a synthetic data generator, that generates realistic microscopy images from unlabeled data.<n>We demonstrate significant improvements over existing techniques in the detection of low-contrast materials such as hexagonal boron nitride.
  arXiv  Detail & Related papers  (2024-12-12T15:01:39Z)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models. In this paper, we investigate how detection performance varies across model backbones, types, and datasets. We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• Few-shot Online Anomaly Detection and Segmentation [29.693357653538474]
  This paper focuses on addressing the challenging yet practical few-shot online anomaly detection and segmentation (FOADS) task. Under the FOADS framework, models are trained on a few-shot normal dataset, followed by inspection and improvement of their capabilities by leveraging unlabeled streaming data containing both normal and abnormal samples simultaneously. In order to achieve improved performance with limited training samples, we employ multi-scale feature embedding extracted from a CNN pre-trained on ImageNet to obtain a robust representation.
  arXiv  Detail & Related papers  (2024-03-27T02:24:00Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• Defect Classification in Additive Manufacturing Using CNN-Based Vision Processing [76.72662577101988]
  This paper examines two scenarios: first, using convolutional neural networks (CNNs) to accurately classify defects in an image dataset from AM and second, applying active learning techniques to the developed classification model. This allows the construction of a human-in-the-loop mechanism to reduce the size of the data required to train and generate training data.
  arXiv  Detail & Related papers  (2023-07-14T14:36:58Z)
• ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization [12.975540251326683]
  We introduce a novel approach based on the Transformer backbone network. We train a Masked Autoencoder (MAE) model solely on normal images. In the subsequent stage, we apply pixel-level data augmentation techniques to generate corrupted normal images. This process allows the model to learn how to repair corrupted regions and classify the status of each pixel.
  arXiv  Detail & Related papers  (2023-03-30T13:11:26Z)
• An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design [55.62660894625669]
  Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. Recent developments in machine learning have provided alternative solutions in replacing the time-consuming lithography simulations with deep neural networks. We propose a litho-aware data augmentation framework to resolve the dilemma of limited data and improve the machine learning model performance.
  arXiv  Detail & Related papers  (2022-10-27T20:53:39Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Negligible effect of brain MRI data preprocessing for tumor segmentation [36.89606202543839]
  We conduct experiments on three publicly available datasets and evaluate the effect of different preprocessing steps in deep neural networks. Our results demonstrate that most popular standardization steps add no value to the network performance. We suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization.
  arXiv  Detail & Related papers  (2022-04-11T17:29:36Z)
• Benchmarking Detection Transfer Learning with Vision Transformers [60.97703494764904]
  complexity of object detection methods can make benchmarking non-trivial when new architectures, such as Vision Transformer (ViT) models, arrive. We present training techniques that overcome these challenges, enabling the use of standard ViT models as the backbone of Mask R-CNN. Our results show that recent masking-based unsupervised learning methods may, for the first time, provide convincing transfer learning improvements on COCO.
  arXiv  Detail & Related papers  (2021-11-22T18:59:15Z)
• Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs [9.237363938772479]
  We perform semantic segmentation of defect types in electron microscopy images of irradiated FeCrAl alloys using a deep learning Mask Regional Convolutional Neural Network (Mask R-CNN) model. We conduct an in-depth analysis of key model performance statistics, with a focus on quantities such as predicted distributions of defect shapes, defect sizes, and defect areal densities. Overall, we find that the current model is a fast, effective tool for automatically characterizing and quantifying multiple defect types in microscopy images.
  arXiv  Detail & Related papers  (2021-10-15T17:57:59Z)
• X-ray Photon-Counting Data Correction through Deep Learning [3.535670189300134]
  We propose a deep neural network based PCD data correction approach. In this work, we first establish a complete simulation model incorporating the charge splitting and pulse pile-up effects. The simulated PCD data and the ground truth counterparts are then fed to a specially designed deep adversarial network for PCD data correction.
  arXiv  Detail & Related papers  (2020-07-06T23:29:16Z)
• Learning-based Defect Recognition for Quasi-Periodic Microscope Images [0.0]
  We propose a semi-supervised machine learning method that assists in the detection of lattice defects from atomic resolution microscope images. It involves a convolutional neural network that classifies image patches as defective or non-defective, a graph-based that chooses one non-defective patch as a model, and finally an automatically generated convolutional filter bank. The algorithm is tested on III-V/Si crystalline materials and successfully evaluated against different metrics, showing promising results even for extremely small training data sets.
  arXiv  Detail & Related papers  (2020-07-02T18:00:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.