no code implementations • 6 Sep 2023 • Ze Peng, Lei Qi, Yinghuan Shi, Yang Gao
Although having attributed it to training dynamics, existing theoretical explanations of activation sparsity are restricted to shallow networks, small training steps and special training, despite its emergence in deep models standardly trained for a large number of steps.
no code implementations • 3 May 2018 • Pei Lv, Meng Wang, Yongbo Xu, Ze Peng, Junyi Sun, Shimei Su, Bing Zhou, Mingliang Xu
When assessing whether an image is of high or low quality, it is indispensable to take personal preference into account.
no code implementations • 2 May 2018 • Jing Wang, Ze Peng, Pei Lv, Junyi Sun, Bing Zhou, Mingliang Xu
The first branch predicts the confidence maps of joints and uses a geometrical transform kernel to propagate information between neighboring joints at the confidence level.