Learnable edge detectors can make deep convolutional neural networks more robust

• Jin Ding ,

  Roles Conceptualization, Data curation, Methodology, Visualization, Writing – original draft, Writing – review & editing

  * E-mail: jding@zust.edu.cn

  Affiliations School of Automation and Electrical Engineering & Key Institute of Robotics of Zhejiang Province, Zhejiang University of Science and Technology, Hangzhou, China, State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, China

  https://orcid.org/0000-0001-6571-8142

  ⨯
• Jie-Chao Zhao,

  Roles Methodology, Validation, Visualization

  Affiliation School of Automation and Electrical Engineering & Key Institute of Robotics of Zhejiang Province, Zhejiang University of Science and Technology, Hangzhou, China

  https://orcid.org/0000-0002-2156-1582

  ⨯
• Yong-Zhi Sun,

  Roles Investigation, Validation, Visualization

  Affiliation School of Automation and Electrical Engineering & Key Institute of Robotics of Zhejiang Province, Zhejiang University of Science and Technology, Hangzhou, China

  ⨯
• Ping Tan,

  Roles Investigation, Supervision, Validation

  Affiliation School of Automation and Electrical Engineering & Key Institute of Robotics of Zhejiang Province, Zhejiang University of Science and Technology, Hangzhou, China

  ⨯
• Jia-Wei Wang,

  Roles Supervision, Validation

  Affiliation School of Automation and Electrical Engineering & Key Institute of Robotics of Zhejiang Province, Zhejiang University of Science and Technology, Hangzhou, China

  ⨯
• Ji-En Ma,

  Roles Software, Supervision, Validation

  Affiliation School of Electrical Engineering, Zhejiang University, Hangzhou, China

  ⨯
• You-Tong Fang

  Roles Supervision

  Affiliation School of Electrical Engineering, Zhejiang University, Hangzhou, China

  ⨯