Deep Evidential Regression
By Alexander Amini, Wilko Schwarting, Ava P. Soleimany, Daniela Rus. Neural Information Processing Systems, 2019
700 citations recorded by the source corpus.
Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust and efficient measures of uncertainty are crucial. While it is possible to train regression networks to output the parameters of a probability distribution by maximizing a Gaussian likelihood function, the resulting model remains oblivious to the underlying confidence of its predictions. In this paper, we propose a novel method for training deterministic NNs to not only estimate the desired target but also the associated evidence in support of that target. We accomplish this by placing evidential priors over our original Gaussian likelihood function and training our NN to infer the hyperparameters of our evidential distribution. We impose priors during training such that the model is penalized when its predicted evidence is not aligned with the correct output. Thus the model estimates not only the probabilistic mean and variance of our target but also the underlying uncertainty associated with each of those parameters. We observe that our evidential regression method learns well-calibrated measures of uncertainty on various benchmarks, scales to complex computer vision tasks, and is robust to adversarial input perturbations.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/14703aaffc186e98bdf3468c3ee70ddce0ccd90d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- A survey of uncertainty in deep neural networks (2021, neutral): “21[101] 22[103] 23[104] 38[68] 39[143] 40[98] 41[43] 42[96] 43[95] 44[67] 45[64] 46[92] 47[72] 48[44] 49[94] 50[35] 51[36] 52[46] 53[71]”
- A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving (2020, methodology): “[67] have shown that it is possible to directly predict the high-order conjugate priors of network output distributions (a Dirichlet prior for the multinomial distribution in classification [24], and a Inverse-Gamma prior for the Gaussian distribution in regression), which are used to estimate…”
- Chemprop: A Machine Learning Package for Chemical Property Prediction (2023, neutral): “The estimation methods include deep ensembles, 77 dropout, 78 mean-variance estimation (MVE), 71 and evidential, 72 as well as a special version of ensemble variance for spectral predictions, 28 and the inherently probabilistic outputs of classification models.”