Steel surface defect recognition is an important part of industrial product detection, which has attracted more and attention in recent years. In the development steel technology, there been a process from manual detection to automatic based on traditional machine learning algorithm, subsequently deep algorithm. this paper, we discuss key hardware systems offer suggestions for related options; ...

In railway surface defect detection applications, supervised deep learning methods suffer from the problems of insufficient samples and an imbalance between positive negative samples. To overcome these problems, we propose a lightweight two-stage architecture including cropping network (RC-Net) defects removal variational autoencoder (DR-VAE), which requires only normal for training to achieve ...

Surface defect detection is an extremely crucial step to ensure the quality of industrial products. Nowadays, convolutional neural networks (CNNs) based on encoder–decoder architecture have achieved tremendous success in various tasks. However, intrinsic locality convolution prevents them from modeling long-range interactions explicitly, making it difficult distinguish pseudo-defects cluttered ...

Quantum field theories (QFT) in the presence of defects exhibit new types anomalies which play an important role constraining defect dynamics and renormalization group (RG) flows. Here we study surface their conformal (CFT) general spacetime dimensions. When is conformal, it characterized by a $b$-anomaly analogous to $c$-anomaly 2d CFTs. The $b$-theorem states that $b$ must monotonically decre...

Defect extremal surface is defined by extremizing the Ryu-Takayanagi formula corrected quantum defect theory. This interesting when AdS bulk contains a brane (or string). We introduce for reflected entropy, which mixed state generalization of entanglement entropy measure. Based on decomposition procedure an with brane, we demonstrate equivalence between and island in AdS$_3$/BCFT$_2$. also comp...