Yes, we Gan: Applying adversarial techniques for autonomous driving

Michal Uřičář; Pavel Křížek; David Hurych; Ibrahim Sobh; Senthil Yogamani; Patrick Denny

doi:10.2352/ISSN.2470-1173.2019.15.AVM-048

Yes, we Gan: Applying adversarial techniques for autonomous driving

Michal Uřičář
, Pavel Křížek
, David Hurych
, Ibrahim Sobh
, Senthil Yogamani
, Patrick Denny

Valeo

Research output: Contribution to journal › Conference article › peer-review

Abstract

Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are perceived as the most impactful direction of machine learning in the last decade. This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc. We formalize and review key applications of adversarial techniques and discuss challenges and open problems to be addressed.

Original language	English
Article number	AVM-048
Journal	IS and T International Symposium on Electronic Imaging Science and Technology
Volume	2019
Issue number	15
DOIs	https://doi.org/10.2352/ISSN.2470-1173.2019.15.AVM-048
Publication status	Published - 13 Jan 2019
Externally published	Yes
Event	2019 Autonomous Vehicles and Machines Conference, AVM 2019 - Burlingame, United States Duration: 13 Jan 2019 → 17 Jan 2019

Access to Document

10.2352/ISSN.2470-1173.2019.15.AVM-048

Cite this

@article{db3297970b0b42e6a7aae87f76464ef0,

title = "Yes, we Gan: Applying adversarial techniques for autonomous driving",

abstract = "Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are perceived as the most impactful direction of machine learning in the last decade. This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc. We formalize and review key applications of adversarial techniques and discuss challenges and open problems to be addressed.",

author = "Michal U{\v r}i{\v c}{\'a}{\v r} and Pavel K{\v r}{\'i}{\v z}ek and David Hurych and Ibrahim Sobh and Senthil Yogamani and Patrick Denny",

note = "Publisher Copyright: {\textcopyright} 2019, Society for Imaging Science and Technology; 2019 Autonomous Vehicles and Machines Conference, AVM 2019 ; Conference date: 13-01-2019 Through 17-01-2019",

year = "2019",

month = jan,

day = "13",

doi = "10.2352/ISSN.2470-1173.2019.15.AVM-048",

language = "English",

volume = "2019",

journal = "IS and T International Symposium on Electronic Imaging Science and Technology",

issn = "2470-1173",

number = "15",

}

TY - JOUR

T1 - Yes, we Gan

T2 - 2019 Autonomous Vehicles and Machines Conference, AVM 2019

AU - Uřičář, Michal

AU - Křížek, Pavel

AU - Hurych, David

AU - Sobh, Ibrahim

AU - Yogamani, Senthil

AU - Denny, Patrick

PY - 2019/1/13

Y1 - 2019/1/13

N2 - Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are perceived as the most impactful direction of machine learning in the last decade. This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc. We formalize and review key applications of adversarial techniques and discuss challenges and open problems to be addressed.

AB - Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are perceived as the most impactful direction of machine learning in the last decade. This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc. We formalize and review key applications of adversarial techniques and discuss challenges and open problems to be addressed.

UR - https://www.scopus.com/pages/publications/85080031995

U2 - 10.2352/ISSN.2470-1173.2019.15.AVM-048

DO - 10.2352/ISSN.2470-1173.2019.15.AVM-048

M3 - Conference article

AN - SCOPUS:85080031995

SN - 2470-1173

VL - 2019

JO - IS and T International Symposium on Electronic Imaging Science and Technology

JF - IS and T International Symposium on Electronic Imaging Science and Technology

IS - 15

M1 - AVM-048

Y2 - 13 January 2019 through 17 January 2019

ER -

Yes, we Gan: Applying adversarial techniques for autonomous driving

Abstract

Access to Document

Other files and links

Fingerprint

Cite this