149 citations · 289 across the 7 of their papers we have counts for
10 papers · 1 filter
LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
Chenxi Liu, Zhaoqi Leng, Pei Sun +5
Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving. However, arguably due to the higher-…
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Zhaoqi Leng, Mingxing Tan, Chenxi Liu +4
Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can…
Are Labels Necessary for Neural Architecture Search?
Chenxi Liu, Piotr Dollár, Kaiming He +3
Existing neural network architectures in computer vision -- whether designed by humans or by machines -- were typically found using both images and their associated labels. In this…
Identifying Model Weakness with Adversarial Examiner
Michelle Shu, Chenxi Liu, Weichao Qiu +1
Machine learning models are usually evaluated according to the average case performance on the test set. However, this is not always ideal, because in some sensitive domains (e.g.…
Rethinking Normalization and Elimination Singularity in Neural Networks
Siyuan Qiao, Huiyu Wang, Chenxi Liu +2
In this paper, we study normalization methods for neural networks from the perspective of elimination singularity. Elimination singularities correspond to the points on the trainin…
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
Siyuan Qiao, Huiyu Wang, Chenxi Liu +2
Batch Normalization (BN) has become an out-of-box technique to improve deep network training. However, its effectiveness is limited for micro-batch training, i.e., each GPU typical…