latest
-
A Peek into Automatic Data Augmentation by Policy Searching
When training a model based on machine-learning (ML) or deep-learning (DL), data augmentation (DA) is a crucial technique to improve the model’s generalization performance and train better representation. However, it relies heavily on human experience or intuition. The ML/DL community has recognized this problem and has been making efforts to find ways to effectively perform […]
2025-09-30 -
Transfer Learning for Industrial Visual Inspection
What is Transfer Learning? In 2012, Alex Krizhevsky introduced AlexNet11, a convolutional neural network (CNN) that overwhelmingly outperformed existing vision algorithms on the ImageNet dataset. Ever since then, CNN has been extensively applied in vision inspection. However, a fatal flaw of CNN compared to existing vision algorithms is that it requires a large amount of […]
2021-07-08