The goal of this workshop on deep learning for vehicle perception is to foster discussion and to accelerate the study
of deep architectures in autonomous driving problems with a focus on the efficiency of the algorithms.
In this edition of the workshop on learning representations for autonomous driving we aim at providing basic
theoretical and practical knowledge to understanding the potential of deep learning architectures as well as to
encourage discussions on the specific challenges within the field of intelligent vehicles and advance the current
status of efficient algorithms by proposing a challenge in this particular topic.
We are soliciting original contributions that address a wide range of theoretical and practical issues including, but
not limited to:
1. Efficient inference with deep neural networks
2. Deep learning for reinforcement learning
3. Uncertainty propagation in deep neural networks
4. Deep neural networks for perception systems in intelligent vehicles
5. Datasets for autonomous driving
6. Low-level vision tasks for Intelligent Vehicles (pedestrian detection, semantic segmentation, instance segmentation...)

Submission Guidelines
Extended abstracts need to be submitted by email to Jose Alvarez
(We will not use the PaperCept system)
Formatting guidelines and submission rules:
1. Maximum of four pages including references
2. IEEE format
3. The extended abstracts will not be published in the proceedings. However they will be published on
this website upon authors’ agreement.
4. The submitted abstract should present recent results, but not necessarily novel ones.
5. All accepted abstracts will be presented as posters at the workshop. We will select a single abstract
which will be additionally given the opportunity for an oral presentation.
6. All abstracts will be reviewed by a program committee and the organizers.


Submission Guidelines
Extended abstracts need to be submitted by email to Jose Alvarez
(We will not use the PaperCept system)
Formatting guidelines and submission rules:
1. Maximum of four pages including references
2. IEEE format
3. The extended abstracts will not be published in the proceedings. However, they will be published on this website upon authors’ agreement.
4. The submitted abstract should present recent results, but not necessarily novel ones.
5. All accepted abstracts will be presented as posters at the workshop. We will select a single abstract which will be additionally given the opportunity for an oral presentation.
6. All abstracts will be reviewed by a program committee and the organizers.