33 citations · 126 across the 14 of their papers we have counts for
6 papers · 1 filter
Probably Unknown: Deep Inverse Sensor Modelling In Radar
Rob Weston, Sarah Cen, Paul Newman +1
Radar presents a promising alternative to lidar and vision in autonomous vehicle applications, able to detect objects at long range under a variety of weather conditions. However,…
Dropout Distillation for Efficiently Estimating Model Confidence
Corina Gurau, Alex Bewley, Ingmar Posner
We propose an efficient way to output better calibrated uncertainty scores from neural networks. The Distilled Dropout Network (DDN) makes standard (non-Bayesian) neural networks m…
Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes
Fabian B. Fuchs, Oliver Groth, Adam R. Kosiorek +4
Visually predicting the stability of block towers is a popular task in the domain of intuitive physics. While previous work focusses on prediction accuracy, a one-dimensional perfo…
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
Adam R. Kosiorek, Hyunjik Kim, Ingmar Posner +1
We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep generative model for videos of moving objects. It can reliably discover and track objects throughout the…
ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking
Oliver Groth, Fabian B. Fuchs, Ingmar Posner +1
Physical intuition is pivotal for intelligent agents to perform complex tasks. In this paper we investigate the passive acquisition of an intuitive understanding of physical princi…
TACO: Learning Task Decomposition via Temporal Alignment for Control
Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter +2
Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies wi…