A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Learning from Incorrectly Labeled Data
2019-08-07
·
via Distill
Section 3.2 of Ilyas et al. (2019) shows that training a model on only adversarial errors leads to non-trivia…
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
