research
∙
09/20/2023
You can have your ensemble and run it too – Deep Ensembles Spread Over Time
Ensembles of independently trained deep neural networks yield uncertaint...
share
research
∙
07/14/2023
HEAL-SWIN: A Vision Transformer On The Sphere
High-resolution wide-angle fisheye images are becoming more and more imp...
research
∙
05/03/2023
Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving
Existing datasets for autonomous driving (AD) often lack diversity and l...
research
∙
01/21/2023
Raw or Cooked? Object Detection on RAW Images
Images fed to a deep neural network have in general undergone several ha...
research
∙
12/13/2022
LidarCLIP or: How I Learned to Talk to Point Clouds
Research connecting text and images has recently seen several breakthrou...
research
∙
12/07/2022
Towards Explainable Motion Prediction using Heterogeneous Graph Representations
Motion prediction systems aim to capture the future behavior of traffic ...
research
∙
10/28/2022
Towards Trustworthy Multi-Modal Motion Prediction: Evaluation and Interpretability
Predicting the motion of other road agents enables autonomous vehicles t...
research
∙
07/01/2022
Masked Autoencoders for Self-Supervised Learning on Automotive Point Clouds
Masked autoencoding has become a successful pre-training paradigm for Tr...
research
∙
05/16/2022
Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml
In this paper, we investigate how field programmable gate arrays can ser...
research
∙
04/21/2022
Learning Future Object Prediction with a Spatiotemporal Detection Transformer
We explore future object prediction – a challenging problem where all ob...
research
∙
03/15/2022
Object Detection as Probabilistic Set Prediction
Accurate uncertainty estimates are essential for deploying deep object d...
research
∙
02/08/2022
Equivariance versus Augmentation for Spherical Images
We analyze the role of rotational equivariance in convolutional neural n...
research
∙
05/28/2021