Tweeted By @svlevine
Deep nets can be overconfident (and wrong) on unfamiliar inputs. What if we directly teach them to be less confident? The idea in RCAD ("Adversarial Unlearning") is to generate images that are hard, and teach it to be uncertain on them: https://t.co/lJf5aVv3Jr
— Sergey Levine (@svlevine) June 17, 2022
A thread: pic.twitter.com/pHj76WHnUA