Unadversarial Examples: Designing Objects for Robust Vision
This work addresses the problem of improving vision model robustness for scenarios where object design can be influenced, benefiting applications like robotics and manufacturing.
This paper introduces a framework for designing "robust objects" that are optimized for confident detection and classification by vision models. This approach significantly improves the performance and robustness of vision models across various tasks, including standard benchmarks, simulated robotics, and real-world experiments.
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 .