Are Vision Transformers Always More Robust Than Convolutional Neural Networks? (2021)
Attributed to:
Understanding scenes and events through joint parsing, cognitive reasoning and lifelong learning
funded by
EPSRC
Abstract
No abstract provided
Bibliographic Information
Publication URI: https://neurips.cc/Conferences/2021/ScheduleMultitrack?event=35490
Type: Conference/Paper/Proceeding/Abstract