论文标题
具有功能变异推理的计算机视觉的可扩展不确定性
Scalable Uncertainty for Computer Vision with Functional Variational Inference
论文作者
论文摘要
随着深度学习继续在计算机视觉中获得成功的应用，量化所有形式的不确定性的能力是其在现实世界中安全可靠的部署的首要要求。在这项工作中，我们利用了功能空间中的变异推断的制定，在该表中，我们将高斯工艺（GPS）与贝叶斯CNN先验和变异家族相关联。由于GP由它们的平均值和协方差函数完全决定，因此我们能够以单个正向通过的成本通过任何选择的CNN体系结构以及任何有监督的学习任务来获得预测不确定性估计。通过利用诱导的协方差矩阵的结构，我们提出了数值有效的算法，该算法可以在高维任务（例如深度估计和语义分割）的背景下进行快速训练。此外，我们提供了足够的条件来构建回归损失函数，其概率对应物与不为人知的不确定性定量兼容。
As Deep Learning continues to yield successful applications in Computer Vision, the ability to quantify all forms of uncertainty is a paramount requirement for its safe and reliable deployment in the real-world. In this work, we leverage the formulation of variational inference in function space, where we associate Gaussian Processes (GPs) to both Bayesian CNN priors and variational family. Since GPs are fully determined by their mean and covariance functions, we are able to obtain predictive uncertainty estimates at the cost of a single forward pass through any chosen CNN architecture and for any supervised learning task. By leveraging the structure of the induced covariance matrices, we propose numerically efficient algorithms which enable fast training in the context of high-dimensional tasks such as depth estimation and semantic segmentation. Additionally, we provide sufficient conditions for constructing regression loss functions whose probabilistic counterparts are compatible with aleatoric uncertainty quantification.
