Paper published in a journal (Scientific congresses, symposiums and conference proceedings)
Leveraging Privileged Information to Limit Distraction in End-to-End Lane Following
ROBINET, François; Demeules, Antoine; FRANK, Raphaël et al.
2020In 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC)
Peer reviewed
 

Files


Full Text
Leveraging-Privileged-Information-to-Limit-Distraction-in-End-to-End-Lane-Following.pdf
Publisher postprint (963.5 kB)
Request a copy

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
end-to-end steering; lane following; visualization; privileged information
Abstract :
[en] Convolutional Neural Networks have been successfully used to steer vehicles using only road-facing cameras. In this work, we investigate the use of Privileged Information for training an end-to-end lane following model. Starting from the prior assumption that such a model should spend a sizeable fraction of its focus on lane markings, we take advantage of lane geometry information available at training time to improve its performance. To this end, we constrain the class of learnable functions by imposing a prior stemming from a lane segmentation task. For each input frame, we compute the set of pixels that most contribute to the prediction of the model using the VisualBackProp method. These pixel-relevance heatmaps are then compared with ground truth lane segmentation masks. A Distraction Loss term is added to the objective to regularize the training process. We learn from real-world data collected using our experimental vehicle and compare the results to those obtained using the simple Mean Squared Error objective. We show that the presence of our regularizer benefits both the performance and the stability of the model across a variety of evaluation metrics. We use a pretrained lane segmentation model without fine-tuning to extract lane marking masks and show that valuable learning signals can be extracted even from imperfect privileged knowledge. This method can be implemented easily and very efficiently on top of an existing architecture, without requiring the addition of any trainable parameter.
Disciplines :
Computer science
Author, co-author :
ROBINET, François ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Demeules, Antoine
FRANK, Raphaël ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
VARISTEAS, Georgios ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
HUNDT, Christian ;  NVIDIA AI Technology Center Luxembourg
External co-authors :
no
Language :
English
Title :
Leveraging Privileged Information to Limit Distraction in End-to-End Lane Following
Publication date :
10 January 2020
Event name :
2020 IEEE 17th Annual Consumer Communications & Networking Conference
Event date :
10-13 January 2020
By request :
Yes
Journal title :
2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC)
ISSN :
2331-9860
Peer reviewed :
Peer reviewed
FnR Project :
FNR13301060 - Machine Learning For Risk Assessment In Semi-autonomous Vehicles, 2018 (01/10/2018-31/08/2022) - François Robinet
Available on ORBilu :
since 21 January 2020

Statistics


Number of views
290 (65 by Unilu)
Number of downloads
16 (14 by Unilu)

Scopus citations®
 
3
Scopus citations®
without self-citations
0
OpenCitations
 
3
OpenAlex citations
 
3

Bibliography


Similar publications



Contact ORBilu