基于自主视觉的太空传播导航是未来轨道服务和空间物流任务的启用技术。虽然一般的计算机愿景受益于机器学习(ML),但由于在空间环境中获取了预期目标的图像的图像的大规模标记数据集的不切实性,培训和验证的星式载体ML模型非常具有挑战性。迄今为止,诸如航天器姿势估计数据集(速度)的现有数据集主要依赖于培训和验证的合成图像,这很容易批量生产,但不能类似于目标星载图像固有的视觉特征和照明可变性。为了弥合当前实践与未来空间任务中的预期应用之间的差距,介绍了速度+:下一代航天器姿势估计数据集具有特定强调域间隙。除了用于训练的60,000个合成图像外,Speed +还包括从Rendezvous和光学导航(Tron)设施的试验台捕获的航天器模型模型的9,531个硬件映像。 Tron是一种专门的机器人测试用机器,能够以准确和最大多样化的姿势标签和高保真星载照明条件捕获任意数量的目标图像。 Speed +用于由平板和欧洲空间机构的平板和高级概念团队共同主办的第二次国际卫星造型估算挑战,以评估和比较在合成图像上培训的星式载ML模型的稳健性。
translated by 谷歌翻译
我们开发了一种新的原则性算法,用于估计培训数据点对深度学习模型的行为的贡献,例如它做出的特定预测。我们的算法估计了AME,该数量量衡量了将数据点添加到训练数据子集中的预期(平均)边际效应,并从给定的分布中采样。当从均匀分布中采样子集时,AME将还原为众所周知的Shapley值。我们的方法受因果推断和随机实验的启发:我们采样了训练数据的不同子集以训练多个子模型,并评估每个子模型的行为。然后,我们使用套索回归来基于子集组成共同估计每个数据点的AME。在稀疏假设($ k \ ll n $数据点具有较大的AME)下,我们的估计器仅需要$ O(k \ log n)$随机的子模型培训,从而改善了最佳先前的Shapley值估算器。
translated by 谷歌翻译
Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been shown to be vulnerable to sophisticated attacks. Recently a set of certified defenses have been introduced, which provide guarantees of robustness to normbounded attacks. However these defenses either do not scale to large datasets or are limited in the types of models they can support. This paper presents the first certified defense that both scales to large networks and datasets (such as Google's Inception network for ImageNet) and applies broadly to arbitrary model types. Our defense, called PixelDP, is based on a novel connection between robustness against adversarial examples and differential privacy, a cryptographically-inspired privacy formalism, that provides a rigorous, generic, and flexible foundation for defense.
translated by 谷歌翻译