Industrial Control Systems depend heavily on security and monitoring protocols. Several tools are available for this purpose, which scout vulnerabilities and take screenshots from various control panels for later analysis. However, they do not adequately classify images into specific control groups, which can difficult operations performed by manual operators. In order to solve this problem, we use transfer learning with five CNN architectures, pre-trained on Imagenet, to determine which one best classifies screenshots obtained from Industrial Controls Systems. Using 337 manually labeled images, we train these architectures and study their performance both in accuracy and CPU and GPU time. We find out that MobilenetV1 is the best architecture based on its 97,95% of F1-Score, and its speed on CPU with 0.47 seconds per image. In systems where time is critical and GPU is available, VGG16 is preferable because it takes 0.04 seconds to process images, but dropping performance to 87,67%.
Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB（弗劳恩霍夫光电、系统技术与图像利用研究所IOSB）；Fraunhofer Center for Machine Learning（弗劳恩霍夫机器学习中心）
SynthRender and I-AsSET: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception
Technical University Berlin, Industrial Automation Technology（柏林技术大学，工业自动化技术）；Mercedes-Benz AG, Future Manufacturing Technologies（梅赛德斯-奔驰公司，未来制造技术）；Technical University Braunschweig, Institute for Cognitive Robotics（不伦瑞克技术大学，认知机器人研究所）
Anomaly Multi-classification in Industrial Scenarios: Transferring Few-shot Learning to a New Task
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能全国重点实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究所）；Xi’an Jiaotong University（西安交通大学）；School of Informatics（信息学院）；Xiamen University（厦门大学）；College of Mechatronics and Control Engineering（机电与控制工程学院）；Shenzhen University（深圳大学）
本文提出工业异常多分类新任务，通过结合 RelationNet 与 PatchCore、伪类数据生成及对比学习，在 MvTec AD 和 MvTec3D AD 上取得优于直接微调 ResNet 的性能。
FedTR: Federated Learning Framework with Transfer Learning for Industrial Visual Inspection
HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University（惠普-南洋理工大学数字制造联合实验室，南洋理工大学）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；Department of Computer Science, Norwegian University of Science and Technology（挪威科技大学计算机科学系）；HP Inc.（惠普公司）；HP Singapore（惠普新加坡公司）
Object Detection Using Sim2Real Domain Randomization for Robotic Applications
Eötvös Loránd Research Network（厄特沃什·罗兰研究网络）；Institute for Computer Science and Control（计算机科学与控制研究所）；Eötvös Loránd University（厄特沃什·罗兰大学）；Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Pavol Jozef Šafárik University（帕沃尔·约瑟夫·沙法里克大学）
在非结构化环境中工作的机器人必须能够感知和解释周围环境。机器人领域基于深度学习的模型的主要障碍之一是缺乏针对不同工业应用的特定领域标记数据。在这篇文章中，我们提出了一种基于域随机化的sim 2 real迁移学习方法用于目标检测，可以自动生成任意大小和对象类型的标记合成数据集。随后，训练最先进的卷积神经网络YOLOv 4来检测不同类型的工业对象。使用所提出的域随机化方法，我们可以将现实差距缩小到令人满意的水平，在zero-shot和one-shot传输的情况下，在包含190张真实图像的手动注释数据集上，分别实现86.32%和97.38%的mAP 50分数。我们的解决方案适合工业应用，因为在GeForce RTX 2080 Ti GPU上，每张图像的数据生成过程不到0.5秒，训练仅持续约12小时。此外，它可以通过仅访问一个真实图像进行训练来可靠地区分类似的对象类别。据我们所知，这是迄今为止唯一满足这些限制的工作。
