no code implementations • 2 Jun 2017 • Nima Tajbakhsh, Jae Y. Shin, Suryakanth R. Gurudu, R. Todd Hurst, Christopher B. Kendall, Michael B. Gotway, Jianming Liang
Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence.
1 code implementation • 3 Feb 2018 • Zongwei Zhou, Jae Y. Shin, Suryakanth R. Gurudu, Michael B. Gotway, Jianming Liang
The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places.