paper-with-me

홈 › Papers

Dropout Distillation for Efficiently Estimating Model Confidence

2018-09-27 · Corina Gurau, Alex Bewley, Ingmar Posner

We propose an efficient way to output better calibrated uncertainty scores from neural networks. The Distilled Dropout Network (DDN) makes standard (non-Bayesian) neural networks more introspective by adding a new training loss which prevents them from being overconfident. Our method is more efficient than Bayesian neural networks or model ensembles which, despite providing more reliable uncertainty scores, are more cumbersome to train and slower to test. We evaluate DDN on the the task of image classification on the CIFAR-10 dataset and show that our calibration results are competitive even when compared to 100 Monte Carlo samples from a dropout network while they also increase the classification accuracy. We also propose better calibration within the state of the art Faster R-CNN object detection framework and show, using the COCO dataset, that DDN helps train better calibrated object detectors.

📄 PDF Abstract BibTeX arXiv:1809.10562

Code (0)

등록된 구현이 없습니다.

Tasks

General Classificationimage-classificationImage Classificationmodelobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
RoIPool 설명 없음
Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…
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

Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout

2023-01-26 · Takuya Hiraoka, Takashi Onishi, Yoshimasa Tsuruoka

In reinforcement learning (RL) with experience replay, experiences stored in a replay buffer influence the RL agent's performance. Information about the influence is valuable for various purposes, including experience cl…

MuJoCoreinforcement-learningReinforcement Learning (RL)

Confidence Calibration for Convolutional Neural Networks Using Structured Dropout

2019-06-23 · Zhilu Zhang, Adrian V. Dalca, Mert R. Sabuncu

In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an effic…

Active LearningBayesian InferenceDiversityEnsemble Learning

Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence

2025-03-18 · Sophia Hager, David Mueller, Kevin Duh, Nicholas Andrews

As large language models (LLMs) are increasingly used for factual question-answering, it becomes more important for LLMs to have the capability to communicate the likelihood that their answer is correct. For these verbal…

Question AnsweringUncertainty Quantification

Ex uno plures: Splitting One Model into an Ensemble of Subnetworks

2021-06-09 · Zhilu Zhang, Vianne R. Gao, Mert R. Sabuncu

Monte Carlo (MC) dropout is a simple and efficient ensembling method that can improve the accuracy and confidence calibration of high-capacity deep neural network models. However, MC dropout is not as effective as more c…

Computational EfficiencyDiversity

Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale

2023-11-27 · Soyed Tuhin Ahmed, Kamal Danouchi, Michael Hefenbrock, Guillaume Prenat 외

Uncertainty estimation in Neural Networks (NNs) is vital in improving reliability and confidence in predictions, particularly in safety-critical applications. Bayesian Neural Networks (BayNNs) with Dropout as an approxim…