June 16, 2022, 1:13 a.m. | Simon Schrodi, Tonmoy Saikia, Thomas Brox

cs.CV updates on arXiv.org arxiv.org

Recent work demonstrated the lack of robustness of optical flow networks to
physical patch-based adversarial attacks. The possibility to physically attack
a basic component of automotive systems is a reason for serious concerns. In
this paper, we analyze the cause of the problem and show that the lack of
robustness is rooted in the classical aperture problem of optical flow
estimation in combination with bad choices in the details of the network
architecture. We show how these mistakes can be …

arxiv cv flow networks robustness understanding

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Technology Consultant Master Data Management (w/m/d)

@ SAP | Walldorf, DE, 69190

Research Engineer, Computer Vision, Google Research

@ Google | Nairobi, Kenya