paper-with-me

Papers

Single Shot MC Dropout Approximation

2020-07-07 · Kai Brach, Beate Sick, Oliver Dürr

Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesian variants of DNNs (BDNNs), such as MC dropout BDNNs, do provide uncertainty measures. However, BDNNs are slow during test time because they rely on a sampling approach. Here we present a single shot MC dropout approximation that preserves the advantages of BDNNs without being slower than a DNN. Our approach is to analytically approximate for each layer in a fully connected network the expected value and the variance of the MC dropout signal. We evaluate our approach on different benchmark datasets and a simulated toy example. We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.

📄 PDF Abstract BibTeX arXiv:2007.03293

Code (1)

kaibrach/Moment-Propagation 공식 구현 tf

Tasks

Autonomous DrivingObject Recognition

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Single-shot Bayesian approximation for neural networks

2023-08-24 · Kai Brach, Beate Sick, Oliver Dürr

Deep neural networks (NNs) are known for their high-prediction performances. However, NNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesi…

Neural Variational Dropout Processes

2021-09-29 · ICLR 2022 4 · Insu Jeon, YoungJin Park, Gunhee Kim

Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs). NVDPs model the con…

Few-Shot LearningImage InpaintingMeta-LearningVariational Inference

Neural Variational Dropout Processes

2025-10-22 · Insu Jeon, Youngjin Park, Gunhee Kim arxiv

Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs). NVDPs model the con…

Few-Shot LearningImage Inpainting

Revisiting Softmax for Uncertainty Approximation in Text Classification

2022-10-25 · Andreas Nugaard Holm, Dustin Wright, Isabelle Augenstein

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) Dropout…

ClassificationDomain Adaptationtext-classificationText Classification

Dropout as a Bayesian Approximation: Appendix

2015-06-06 · Yarin Gal, Zoubin Ghahramani

We show that a neural network with arbitrary depth and non-linearities, with dropout applied before every weight layer, is mathematically equivalent to an approximation to a well known Bayesian model. This interpretation…

Deep Learning