Alwin Hoffmann

RO
h-index4
3papers
19citations
Novelty30%
AI Score24

3 Papers

CVApr 14, 2025
Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics

Nikolai Röhrich, Alwin Hoffmann, Richard Nordsieck et al.

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.

ROJan 22, 2020
Opportunities and Limitations of Mixed Reality Holograms in Industrial Robotics

Michael Filipenko, Andreas Angerer, Alwin Hoffmann et al.

This paper introduces two case studies combining the field of industrial robotics with Mixed Reality (MR). The goal of those case studies is to get a better understanding of how MR can be useful and what are the limitations. The first case study describes an approach to visualize the digital twin of a robot arm. The second case study aims at facilitating the commissioning of industrial robots. Furthermore, this paper reports the experiences gained by implementing those two scenarios and discusses the limitations.

ROMar 27, 2013
A Graphical Language for Real-Time Critical Robot Commands

Andreas Angerer, Remi Smirra, Alwin Hoffmann et al.

Industrial robotics is characterized by sophisticated mechanical components and highly-developed real-time control algorithms. However, the efficient use of robotic systems is very much limited by existing proprietary programming methods. In the research project SoftRobot, a software architecture was developed that enables the programming of complex real-time critical robot tasks with an object-oriented general purpose language. On top of this architecture, a graphical language was developed to ease the specification of complex robot commands, which can then be used as part of robot application workflows. This paper gives an overview about the design and implementation of this graphical language and illustrates its usefulness with some examples.