38 citations · 78 across the 22 of their papers we have counts for
5 papers · 1 filter
MixupE: Understanding and Improving Mixup from Directional Derivative Perspective
Yingtian Zou, Vikas Verma, Sarthak Mittal +6
Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels.…
Towards Improved Learning in Gaussian Processes: The Best of Two Worlds
Rui Li, ST John, Arno Solin
Gaussian process training decomposes into inference of the (approximate) posterior and learning of the hyperparameters. For non-Gaussian (non-conjugate) likelihoods, two common cho…
Fantasizing with Dual GPs in Bayesian Optimization and Active Learning
Paul E. Chang, Prakhar Verma, ST John +3
Gaussian processes (GPs) are the main surrogate functions used for sequential modelling such as Bayesian Optimization and Active Learning. Their drawbacks are poor scaling with dat…
Expansion of Visual Hints for Improved Generalization in Stereo Matching
Andrea Pilzer, Yuxin Hou, Niki Loppi +2
We introduce visual hints expansion for guiding stereo matching to improve generalization. Our work is motivated by the robustness of Visual Inertial Odometry (VIO) in computer vis…
A Look at Improving Robustness in Visual-inertial SLAM by Moment Matching
Arno Solin, Rui Li, Andrea Pilzer
The fusion of camera sensor and inertial data is a leading method for ego-motion tracking in autonomous and smart devices. State estimation techniques that rely on non-linear filte…