Search Results for author:
Found 2 papers, 0 papers with code
Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs
The relaxed kernel orthogonality achieves enhanced performance on models with increased capacity, shedding light on the burden of strict kernel orthogonality on deep model performance.
How many labeled license plates are needed?
As a large amount of labeled data is typically difficult to collect and even more difficult to annotate, data augmentation and data generation are widely used in the process of training deep neural networks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
