[visionlist] ECCV 2020 Workshop: Adversarial Robustness in the Real World

[Adam Kortylewski]

ECCV 2020 - Workshop on Adversarial Robustness in the Real World

Glasgow- Scotland - 23th August 2020

In conjunction with ECCV 2020 - European Conference on Computer Vision

 Web: https://eccv20-adv-workshop.github.io



********************************************************

_________________

IMPORTANT DATES

_________________



Full Paper Submission: July 10th 2020, Anywhere on Earth (AoE)

Notification of Acceptance: July 30th, 2020, Anywhere on Earth (AoE)



________________

CALL FOR PAPERS

________________



Computer vision systems nowadays have advanced performance but research in adversarial machine learning also shows that they are not as robust as the human vision system. In this context, perturbation-based adversarial examples have received great attention. Moreover, recent work has shown that real-world adversarial examples exist when objects are partially occluded or viewed in previously unseen poses and environments (such as different weather conditions). Discovering and harnessing those adversarial examples provides opportunities for understanding and improving computer vision systems in real-world environments. In particular, deep models with structured internal representations seem to be a promising approach to enhance robustness in the real world, while also being able to explain their predictions.

In this workshop, we aim to bring together researches from the fields of adversarial machine learning, robust vision and explainable AI to discuss recent research and future directions for adversarial robustness and explainability, with a particular focus on real-world scenarios.

We invite submissions on any aspect of adversarial robustness in real-world computer vision. This includes, but is not limited to:

- Discovery of real-world adversarial examples

- Novel architectures with robustness to occlusion, viewpoint and other real-world domain shifts

- Domain adaptation techniques for building robust vision system in the real world

- Datasets for evaluating model robustness

- Adversarial machine learning for diagnosing and understanding limitations of computer vision systems

- Improving generalization performance of computer vision systems to out-of-distribution samples

- Structured deep models

- Explainable AI



_________________

INVITED SPEAKERS

_________________



- Matthias Bethge, University of Tübingen, Germany

- Alan Yuille, Johns Hopkins University, USA

- Andreas Geiger, University of Tübingen, Germany

- Raquel Urtasun, University of Toronto, Canada

- Honglak Lee, University of Michigan, USA

- Bo Li, University of Illinois at Urbana-Champaign, USA

- Judy Hoffman, Georgia Tech, USA

- Daniel Fremont, UC Santa Cruz, USA

- George J. Pappas, University of Pennsylvania



____________

SUBMISSION AND REVISION

____________



All submissions will be handled electronically via the conference’s CMT Website: https://cmt3.research.microsoft.com/AROW2020/



The format for paper submission is the same as the ECCV 2020 main conference. Submissions need to be anonymized and follow the ECCV 2020 Author Instructions<https://eccv2020.eu/author-instructions/>:

https://eccv2020.eu/author-instructions/



AROW reviewing will be double-blind. Each submission will be reviewed by at least three reviewers for originality, significance, clarity, soundness, relevance and technical contents.



The workshop considers two types of submissions: (1) Long Paper: Papers are limited to 14 pages excluding references and will be included in the official ECCV proceedings; (2) Extended Abstract: Papers are limited to 7 pages excluding references and will NOT be included in the official ECCV proceedings. Based on the PC recommendations, the accepted long papers/extended abstracts will be allocated either a contributed talk or a poster presentation.



Authors may optionally submit additional material that could not be included in the main paper due to constraints of format (e.g., a video), space (e.g., a proof of a theorem or an extra figure or table) or anonymity.

 _________________

WORKSHOP ORGANIZERS

_________________



Adam Kortylewski, Johns Hopkins University, USA

Cihang Xie, Johns Hopkins University, USA

Song Bai, University of Oxford, UK

Zhaowei Cai, Amazon, USA

Yingwei Li, Johns Hopkins University, USA

Andrei Barbu, MIT, USA

Wieland Brendel, University of Tübingen, Germany

Nuno Vasconcelos, UCSD, USA

Andrea Vedaldi, University of Oxford, UK

Philip H.S. Torr, University of Oxford, UK

Rama Chellappa, University of Maryland, USA

Alan Yuille, Johns Hopkins University, USA

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20200623/c5f4cf54/attachment.html>