Recent advances in high-fidelity simulators have enabled closed-loop tra...
Network pruning can significantly reduce the computation and memory foot...
Recent work on hyperparameters optimization (HPO) has shown the possibil...
Self-supervised representation learning is able to learn semantically
me...
In this paper, we address the important problem in self-driving of
forec...
3D shape completion for real data is important but challenging, since pa...
Deep neural nets typically perform end-to-end backpropagation to learn t...
Obtaining precise instance segmentation masks is of high importance in m...
In this paper, we propose PolyTransform, a novel instance segmentation
a...
Self-driving vehicles plan around both static and dynamic objects, apply...
Recent studies on catastrophic forgetting during sequential learning
typ...
In this paper, we propose the differentiable mask-matching network (DMM-...
Point clouds are the native output of many real-world 3D sensors. To bor...
In this paper we tackle the problem of scene flow estimation in the cont...
In this paper, we propose a unified panoptic segmentation network (UPSNe...
A useful computation when acting in a complex environment is to infer th...
In this paper, we revisit the recurrent back-propagation (RBP) algorithm...
Convolutional neural networks (CNNs) are inherently limited to model
geo...
Deep convolutional neutral networks have achieved great success on image...