Estimating uncertainty in image-to-image networks is an important task, particularly as such networks are being increasingly deployed in the biological and medical imaging realms. In this paper, we introduce a new approach to this problem based on masking. Given an existing image-to-image network, our approach computes a mask such that the distance between the masked reconstructed image and the masked true image is guaranteed to be less than a specified threshold, with high probability. The mask thus identifies the more certain regions of the reconstructed image. Our approach is agnostic to the underlying image-to-image network, and only requires triples of the input (degraded), reconstructed and true images for training. Furthermore, our method is agnostic to the distance metric used. As a result, one can use $L_p$-style distances or perceptual distances like LPIPS, which contrasts with interval-based approaches to uncertainty. Our theoretical guarantees derive from a conformal calibration procedure. We evaluate our mask-based approach to uncertainty on image colorization, image completion, and super-resolution tasks, demonstrating high quality performance on each.
翻译:估计图像到图像网络的不确定性是一项重要任务, 特别是因为这些网络正越来越多地部署在生物和医学成像领域。 在本文中, 我们引入了基于遮罩的新方法。 鉴于已有的图像到图像网络, 我们的方法计算了一个面罩, 从而保证蒙面重建图像与蒙面真实图像之间的距离低于特定阈值, 概率高。 遮罩由此确定了重建图像的更特定区域。 我们的方法是对基本图像到图像网络的不可知性, 只需要输入( 降级的)、 重建的和真实的图像的三倍用于培训。 此外, 我们的方法对所使用的远度测量值是不可知的。 因此, 我们的方法可以使用 $L_ p$ 模式的距离或像 LPIPS 这样的感知性距离, 与以间隔为基础的不确定性方法形成对照。 我们的理论保证来自一个统一的校准程序。 我们评估了我们基于遮罩的图像色化、 图像完成和超分辨率任务的不确定性的方法, 展示了每个图像的高质量性能 。