Learning Representations Robust to Group Shifts and Adversarial Examples

arxiv(2022)

引用 0|浏览19
暂无评分
摘要
Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of methods to improve model robustness, including adversarial training and distributionally robust optimization. Though both of these two methods are geared towards learning robust models, they have essentially different motivations: adversarial training attempts to train deep neural networks against perturbations, while distributional robust optimization aims at improving model performance on the most difficult "uncertain distributions". In this work, we propose an algorithm that combines adversarial training and group distribution robust optimization to improve robust representation learning. Experiments on three image benchmark datasets illustrate that the proposed method achieves superior results on robust metrics without sacrificing much of the standard measures.
更多
查看译文
关键词
representations robust,adversarial examples,group shifts,learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要