Reference : Weakly-Supervised Free Space Estimation through Stochastic Co-Teaching
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
Computational Sciences
http://hdl.handle.net/10993/50199
Weakly-Supervised Free Space Estimation through Stochastic Co-Teaching
English
Robinet, François mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SEDAN >]
Parera, Claudia mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SEDAN >]
Hundt, Christian mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Frank, Raphaël mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SEDAN >]
4-Jan-2022
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2022
618-627
Yes
No
International
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops 2022
4-01-2022 to 8-01-2022
HI
[en] weak supervision ; Free space ; co-teaching
[en] Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches train a segmentation model using an annotated dataset. The training data needs to capture the wide variety of environments and weather conditions encountered at runtime, making the annotation cost prohibitively high. In this work, we propose a novel approach for obtaining free space estimates from images taken with a single road-facing camera. We rely on a technique that generates weak free space labels without any supervision, which are then used as ground truth to train a segmentation model for free space estimation. Our work differs from prior attempts by explicitly taking label noise into account through the use of Co-Teaching. Since Co-Teaching has traditionally been investigated in classification tasks, we adapt it for segmentation and examine how its parameters affect performances in our experiments. In addition, we propose Stochastic Co-Teaching, which is a novel method to select clean samples that leads to enhanced results. We achieve an IoU of 82.6%, a Precision of 90.9%, and a Recall of 90.3%. Our best model reaches 87% of the IoU, 93% of the Precision, and 93% of the Recall of the equivalent fully-supervised baseline while using no human annotations. To the best of our knowledge, this work is the first to use Co-Teaching to train a free space segmentation model under explicit label noise. Our implementation and trained models are freely available online.
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Services and Data management research group (SEDAN)
Researchers ; Professionals ; Students
http://hdl.handle.net/10993/50199
https://openaccess.thecvf.com/content/WACV2022W/HPIV/html/Robinet_Weakly-Supervised_Free_Space_Estimation_Through_Stochastic_Co-Teaching_WACVW_2022_paper.html
FnR ; FNR13301060 > François Robinet > MASSIVE > Machine Learning For Risk Assessment In Semi-autonomous Vehicles > 01/10/2018 > 31/08/2022 > 2018

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Robinet_Weakly-Supervised_Free_Space_Estimation_Through_Stochastic_Co-Teaching_WACVW_2022_paper.pdfPublisher postprint736.33 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.