30 citations · 38 across the 5 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023
Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs
Changhao Wu, Shenan Zhang, Fangsong Long +2
Orthogonality regularization has been developed to prevent deep CNNs from training instability and feature redundancy. Among existing proposals, kernel orthogonality regularization…
cs.CV2018
How many labeled license plates are needed?
Changhao Wu, Shugong Xu, Guocong Song +1
Training a good deep learning model often requires a lot of annotated data. As a large amount of labeled data is typically difficult to collect and even more difficult to annotate,…