Dropout Distillation for Efficiently Estimating Model Confidence
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.
Code (0)
등록된 구현이 없습니다.
Tasks
General Classificationimage-classificationImage Classificationmodelobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout
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
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 LearningUncertainty Distillation: Teaching Language Models to Express Semantic Confidence
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 QuantificationEx uno plures: Splitting One Model into an Ensemble of Subnetworks
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 EfficiencyDiversityScale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale
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…