Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics
This work addresses the problem of data scarcity and domain dissimilarity in microelectronics defect detection for industry applications, offering an incremental improvement by adapting existing self-supervised methods to a specific domain.
The paper tackles the challenge of applying vision transformers to microelectronics defect detection despite limited labeled data by proposing a self pre-training framework using masked autoencoders on a small dataset of less than 10,000 images. The result is substantial performance gains over supervised ViT, ViT pre-trained on natural images, and state-of-the-art CNN models, with interpretability analysis showing improved attention to defect-relevant features.
While transformers have surpassed convolutional neural networks (CNNs) in various computer vision tasks, microelectronics defect detection still largely relies on CNNs. We hypothesize that this gap 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 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. We address this challenge through self pre-training, where models are pre-trained directly on the target dataset, rather than another dataset. We propose a resource-efficient vision transformer (ViT) pre-training framework for defect detection in microelectronics based on masked autoencoders (MAE). We perform pre-training and defect detection using a dataset of less than 10,000 scanning acoustic microscopy (SAM) images. 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 microelectronics. Additionally, interpretability analysis reveals that our self pre-trained models attend to defect-relevant features such as cracks in the solder material, while baseline models often attend to spurious patterns. This shows that our approach yields defect-specific feature representations, resulting in more interpretable and generalizable transformer models for this data-sparse domain.