1.1k citations · 2.5k across the 39 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
cs.LG2019★ 10 cited
Angular Visual Hardness
Beidi Chen, Weiyang Liu, Zhiding Yu +4
Recent convolutional neural networks (CNNs) have led to impressive performance but often suffer from poor calibration. They tend to be overconfident, with the model confidence not…
cs.LG2019★ 11 cited
Neural Similarity Learning
Weiyang Liu, Zhen Liu, James M. Rehg +1
Inner product-based convolution has been the founding stone of convolutional neural networks (CNNs), enabling end-to-end learning of visual representation. By generalizing inner pr…
cs.CV2019★ 3 cited
Regularizing Neural Networks via Minimizing Hyperspherical Energy
Rongmei Lin, Weiyang Liu, Zhen Liu +5
Inspired by the Thomson problem in physics where the distribution of multiple propelling electrons on a unit sphere can be modeled via minimizing some potential energy, hyperspheri…