Stochastic Weight Perturbations Along the Hessian: A Plug-and-Play Method to Compute Uncertainty.
UNSURE@MICCAI(2022)
摘要
An uncertainty score along with predictions of a deep learning model is necessary for acceptance and often mandatory to satisfy regulatory requirements. The predominant method to generating uncertainty scores is to utilize a Bayesian formulation of deep learning. In this paper, we present a plug-and-play method to obtain samples from an already optimized model. Specifically, we present a simple, albeit principled methodology, to generate a number of models by sampling along the eigen directions of the Hessian of the converged minimum. We demonstrate the utility of our methods on two challenging medical ultrasound imaging problems - cardiac view recognition and kidney segmentation.
更多查看译文
关键词
Uncertainty,Deep learning,Calibration,Medical imaging
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要