We present a new certification method for image and point cloud segmentation based on randomized smoothing. The method leverages a novel scalable algorithm for prediction and certification that correctly accounts for multiple testing, necessary for ensuring statistical guarantees. The key to our approach is reliance on established multiple-testing correction mechanisms as well as the ability to abstain from classifying single pixels or points while still robustly segmenting the overall input. Our experimental evaluation on synthetic data and challenging datasets, such as Pascal Context, Cityscapes, and ShapeNet, shows that our algorithm can achieve, for the first time, competitive accuracy and certification guarantees on real-world segmentation tasks. We provide an implementation at https://github.com/eth-sri/segmentation-smoothing.
翻译:我们提出了一个基于随机平滑的图像和点云分解的新的认证方法。该方法利用一种新的可缩放的预测和认证算法,正确计算多种测试,这是确保统计保障所必需的。我们方法的关键在于依靠既定的多重测试校正机制,以及避免对单一像素或点进行分类的能力,同时仍然对总体投入进行稳健的分解。我们对合成数据和具有挑战性的数据集,如帕斯卡尔环境、城市景象和ShapeNet的实验性评价表明,我们的算法首次能够实现真实世界分解任务的竞争性准确性和认证保证。我们在https://github.com/eth-sri/sectionmentation-smoozing上提供了一个实施程序。