Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate — mentioned by amcoastal

Wed, 27 May 2020 14:23:50 GMT

Yes, definitely. Though there has been some interesting papers recently on this using different methods to approximate bayesian posteriors in NN's. One of the most recent ones (Mi et al., 2019; https://arxiv.org/abs/1910.04858) that benchmarks a few different methods -- infer-dropout, infer-transformation, and infer-noise -- are all promising for different applications and neural network models (black, 'grey', 'white' box).

Paper and discussion history. A mention is not an endorsement.

Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate · HackerPapers discussions

Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate — mentioned by amcoastal