论文标题
非对抗性示例：设计对象的稳健视力
Unadversarial Examples: Designing Objects for Robust Vision
论文作者
论文摘要
我们研究一类现实的计算机视觉设置，其中可以影响所识别的对象的设计。我们开发了一个利用这种能力来显着提高视力模型的性能和鲁棒性的框架。该框架利用了现代机器学习算法的敏感性输入扰动，以设计“稳健对象”，即明确优化以确保检测或分类的对象。我们证明了该框架对从标准基准，（仿真）机器人技术到现实世界实验的各种基于视觉的任务的功效。我们的代码可以在https://git.io/unadversarial上找到。
We study a class of realistic computer vision settings wherein one can influence the design of the objects being recognized. We develop a framework that leverages this capability to significantly improve vision models' performance and robustness. This framework exploits the sensitivity of modern machine learning algorithms to input perturbations in order to design "robust objects," i.e., objects that are explicitly optimized to be confidently detected or classified. We demonstrate the efficacy of the framework on a wide variety of vision-based tasks ranging from standard benchmarks, to (in-simulation) robotics, to real-world experiments. Our code can be found at https://git.io/unadversarial .
