no code implementations • 16 Jun 2023 • Changhao Wu, Shenan Zhang, Fangsong Long, Ziliang Yin, Tuo Leng
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.
no code implementations • 25 Aug 2018 • Changhao Wu, Shugong Xu, Guocong Song, Shunqing Zhang
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.