research
∙
05/22/2023
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
Data augmentation methods have played an important role in the recent ad...
share
research
∙
10/24/2022
LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations
Data augmentations are important in training high-performance 3D object ...
research
∙
10/11/2022
What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries
Deep neural network classifiers partition input space into high confiden...
research
∙
04/26/2022
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Cross-entropy loss and focal loss are the most common choices when train...
research
∙
07/20/2021
Learn2Hop: Learned Optimization on Rough Landscapes
Optimization of non-convex loss surfaces containing many local minima re...
research
∙
10/15/2020
Does Data Augmentation Benefit from Split BatchNorms
Data augmentation has emerged as a powerful technique for improving the ...
research
∙
04/02/2020