activity
20092025
most citedImproved Adversarial Systems for 3D Object Generation and Reconstruction

64 citations · 170 across the 33 of their papers we have counts for

collaborators
Showing 2019Show all

8 papers · 1 filter

eess.IV20191 cited

Detecting GAN generated errors

Xiru Zhu, Fengdi Che, Tianzi Yang +3

Despite an impressive performance from the latest GAN for generating hyper-realistic images, GAN discriminators have difficulty evaluating the quality of an individual generated sa…

cs.LG2019

Deep learning for Aerosol Forecasting

Caleb Hoyne, S. Karthik Mukkavilli, David Meger

Reanalysis datasets combining numerical physics models and limited observations to generate a synthesised estimate of variables in an Earth system, are prone to biases against grou…

cs.RO2019

Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning

Sahand Rezaei-Shoshtari, David Meger, Inna Sharf

Motivated by the recursive Newton-Euler formulation, we propose a novel cascaded Gaussian process learning framework for the inverse dynamics of robot manipulators. This approach l…

stat.ML20191 cited

Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales

Sanjay Thakur, Herke Van Hoof, Gunshi Gupta +1

Neural Network based controllers hold enormous potential to learn complex, high-dimensional functions. However, they are prone to overfitting and unwarranted extrapolations. PAC Ba…

cs.LG2019

Learning Domain Randomization Distributions for Training Robust Locomotion Policies

Melissa Mozifian, Juan Camilo Gamboa Higuera, David Meger +1

Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policie…

cs.CV2019

Human Motion Prediction via Pattern Completion in Latent Representation Space

Yi Tian Xu, Yaqiao Li, David Meger

Inspired by ideas in cognitive science, we propose a novel and general approach to solve human motion understanding via pattern completion on a learned latent representation space.…