activity
20162023
most citedPIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation

38 citations · 78 across the 22 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.LG2022★ 2 cited

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.…

cs.LG2022

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…

cs.LG2022

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…

cs.CV2022

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…

cs.RO2022

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…