This repo is a collection of AWESOME papers/codes/blogs about Uncertainty and Deep learning, including papers, code, etc. Feel free to star and fork.
if you think we missed a paper, please send us an email at: gianni.franchi at ensta-paris.fr with the following subject awesome-uncertainty-deeplearning. (tell us where it is published, and send us a GitHub link and arxiv link if they are available)
- Contents
- Papers
- Survey
- Theory
- Ensemble/Bayesian-Methods
- Sampling/Dropout-based-Methods
- Learning-loss-distributions/Auxiliary-network-Methods
- Data-augmentation/Generation-based-Methods
- Calibration
- Prior-networks/Evidential-deep-learning
- Deterministic-Uncertainty-Methods
- Quantile-Regression/Predicted-Intervals
- Applications
- Datasets and Benchmarks
- Library
- Lectures and Tutorials
- Other Resources
Arxiv
- Ensemble deep learning: A review. [arxiv2021]
- A survey of uncertainty in deep neural networks.[arxiv2021]
- A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation [arxiv2021]
Conference
- A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications[AISafety2020 Workshop]
Journal
- Predictive inference with the jackknife+." [The Annals of Statistic(2021)]
- A review of uncertainty quantification in deep learning: Techniques, applications and challenges [Information Fusion 2021]
- A Survey on Uncertainty Estimation in Deep Learning Classification Systems from a Bayesian Perspective [ACM2021]
- Uncertainty in big data analytics: survey, opportunities, and challenges [Journal of Big Data2019]
Arxiv
- Bayesian Model Selection, the Marginal Likelihood, and Generalization [arxiv2022]
- Testing for Outliers with Conformal p-values [arxiv2021] [python]
- Efficient Gaussian Neural Processes for Regression [arxiv2021]
- DEUP: Direct Epistemic Uncertainty Prediction [arxiv2020]
- A higher-order swiss army infinitesimal jackknife [arxiv2019]
- With malice towards none: Assessing uncertainty via equalized coverage [arxiv2019]
Conference
- Top-label calibration and multiclass-to-binary reductions [ICLR2022]
- Neural Variational Gradient Descent [AABI2022]
- Bayesian Optimization with High-Dimensional Outputs [NIPS2021]
- Residual Pathway Priors for Soft Equivariance Constraints [NIPS2021]
- Dangers of Bayesian Model Averaging under Covariate Shift [NIPS2021] [Tensorflow]
- A Mathematical Analysis of Learning Loss for Active Learning in Regression [CVPR2021Workshop]
- Uncertainty in Gradient Boosting via Ensembles [ICLR2021] [Pytorch]
- Evidential Deep Learning to Quantify Classification Uncertainty [NIPS2018] [Pytorch]
- On the accuracy of influence functions for measuring group effects [NIPS2018]
- To Trust Or Not To Trust A Classifier [NIPS2018] [python]
Journal
- Multivariate Uncertainty in Deep Learning [TNNLS2021]
- A General Framework for Uncertainty Estimation in Deep Learning [RAL2020]
- Adaptive nonparametric confidence sets [The Annals of Statistic(2006)]
Arxiv
- Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks [arxiv2022]
- Confident Neural Network Regression with Bootstrapped Deep Ensembles [arxiv2022] [Tensorflow]
- Repulsive Deep Ensembles are Bayesian [arxiv2021]
- Bayesian Neural Networks with Soft Evidence [arxiv2020] [Pytorch]
- On Batch Normalisation for Approximate Bayesian Inference [arxiv2020]
- Bayesian neural network via stochastic gradient descent [arxiv2020]
- Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification [arxiv2020] [Pytorch]
- Deep Ensembles: A Loss Landscape Perspective [arxiv2019]
- Diversity with Cooperation: Ensemble Methods for Few-Shot Classification [arxiv2019]
- Ensemble Distribution Distillation [arxiv2018]
Conference
- Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity [ICLR2022] [Pytorch]
- Masksembles for Uncertainty Estimation [CVPR2021] [Pytorch/Tensorflow]
- On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks [UAI2021]
- Learnable uncertainty under Laplace approximations [UAI2021]
- Real-time uncertainty estimation in computer vision via uncertainty-aware distribution distillation [WACV2021]
- Uncertainty in Gradient Boosting via Ensembles [ICLR2021] [Pytorch]
- Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles [AAAI2020]
- Hyperparameter Ensembles for Robustness and Uncertainty Quantification [NIPS2020]
- Bayesian Uncertainty Estimation for Batch Normalized Deep Networks [ICML2020]
- BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning [ICLR2020] [Tensorflow] [Pytorch]
- A General Framework for Uncertainty Estimation in Deep Learning [ICRA2020]
- TRADI: Tracking deep neural network weight distributions for uncertainty estimation [ECCV2020] [Pytorch]
- A Simple Baseline for Bayesian Uncertainty in Deep Learning [NIPS2019] [Pytorch]
- Lightweight Probabilistic Deep Networks [CVPR2018] [Pytorch]
- Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning [ICML2018]
- High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach [ICML2018] [Tensorflow]
- Uncertainty estimates and multi-hypotheses networks for optical flow [ECCV2018] [Tensorflow]
- Simple and scalable predictive uncertainty estimation using deep ensembles [NIPS2017]
Journal
- One Versus all for deep Neural Network for uncertaInty (OVNNI) quantification [IEEE Access2021]
- Bayesian modeling of uncertainty in low-level vision [IJCV1990]
Arxiv
- SoftDropConnect (SDC) – Effective and Efficient Quantification of the Network Uncertainty in Deep MR Image Analysis [arxiv2022]
Conference
- Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate [AAAI2022]
- Dropout Sampling for Robust Object Detection in Open-Set Conditions [ICRA2018]
- Concrete Dropout [NIPS2017]
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning [ICML2016]
Journal
- article
Arxiv
- DEUP: Direct Epistemic Uncertainty Prediction [arxiv2020]
- Learning Confidence for Out-of-Distribution Detection in Neural Networks[arxiv2018]
Conference
- Learning Structured Gaussians to Approximate Deep Ensembles [CVPR2022]
- SLURP: Side Learning Uncertainty for Regression Problems [BMVC2021] [Pytorch]
- Learning to Predict Error for MRI Reconstruction [MICCAI2021]
- A Mathematical Analysis of Learning Loss for Active Learning in Regression [CVPR2021Workshop]
- Learning Loss for Test-Time Augmentation [NIPS2020]
- On the uncertainty of self-supervised monocular depth estimation [CVPR2020] [Pytorch]
- Addressing failure prediction by learning model confidence [NeurIPS2019][Pytorch]
- Learning loss for active learning [CVPR2019] [Pytorch] (unofficial codes)
- Structured Uncertainty Prediction Networks [CVPR2018] [Tensorflow]
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?[NIPS2017]
- Estimating the Mean and Variance of the Target Probability Distribution [(ICNN94)]
Journal
- Confidence Estimation via Auxiliary Models [TPAMI2021]
Arxiv
- Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates [arxiv2021]
- Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [arxiv2021]
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures." [arxiv2021]
- Quantifying uncertainty with GAN-based priors [arxiv2019]
Conference
- Robust Semantic Segmentation with Superpixel-Mix [BMVC2021]
- MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks [ICCV2021] [Pytorch]
- Training independent subnetworks for robust prediction [ICLR2021]
- Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement [ICCVWorkshop2021]
- Mix-n-match: Ensemble and compositional methods for uncertainty calibration in deep learning [ICML2020]
- Uncertainty-Aware Deep Classifiers using Generative Models [AAAI2020]
- Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation [ECCV2020] [Pytorch]
- Detecting the Unexpected via Image Resynthesis [ICCV2019] [Pytorch]
- On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks [NIPS2019]
Journal
- article
Arxiv
- Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification [arxiv2021]
- The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration [arxiv2021][Pytorch]
- Evaluating and Calibrating Uncertainty Prediction in Regression Tasks [arxiv2020]
- Towards Understanding Label Smoothing [arxiv2020]
- An Investigation of how Label Smoothing Affects Generalization[arxiv2020]
- On Fairness and Calibration[arxiv2017]
Conference
- Top-label calibration and multiclass-to-binary reductions [ICLR2022]
- From label smoothing to label relaxation [AAAI2021]
- Calibrating Deep Neural Networks using Focal Loss [NIPS2020] [Pytorch]
- Stationary activations for uncertainty calibration in deep learning [NIPS2020]
- Mix-n-match: Ensemble and compositional methods for uncertainty calibration in deep learning [ICML2020]
- Regularization via structural label smoothing [ICML2020]
- Well-Calibrated Regression Uncertainty in Medical Imaging with Deep Learning [MIDL2020] [Pytorch]
- Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision [CVPRW2020] [Pytorch]
- When does label smoothing help? [NIPS2019]
- Verified Uncertainty Calibration [NIPS2019]
- Generalized zero-shot learning with deep calibration network [NIPS2018]
- Measuring Calibration in Deep Learning [CVPRW2019]
- Accurate Uncertainties for Deep Learning Using Calibrated Regression [ICML2018]
- On calibration of modern neural networks. [ICML2017]
Journal
- Calibrated Prediction Intervals for Neural Network Regressors [IEEE Access 2018][Python]
Arxiv
- Effective Uncertainty Estimation with Evidential Models for Open-World Recognition [arxiv2022]
- A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation [arxiv2021]
- Regression Prior Networks [arxiv2020]
- Uncertainty estimation in deep learning with application to spoken language assessment[phdthesis2019]
- Inhibited softmax for uncertainty estimation in neural networks [arxiv2018].
Conference
- Improving Evidential Deep Learning via Multi-task Learning [AAAI2022]
- Evaluating robustness of predictive uncertainty estimation: Are Dirichlet-based models reliable? [ICML2021]
- Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts [NIPS2020] [Pytorch]
- Conservative Uncertainty Estimation By Fitting Prior Networks [ICLR2020]
- Noise Contrastive Priors for Functional Uncertainty [UAI2020]
- Deep Evidential Regression [NIPS2020] [Tensorflow]
- Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness [NIPS2019]
- Evidential Deep Learning to Quantify Classification Uncertainty [NIPS2018] [Pytorch]
- Predictive uncertainty estimation via prior networks [NIPS2018]
Journal
- Information Aware max-norm Dirichlet networks for predictive uncertainty estimation [NeuralNetworks2021]
Arxiv
- Deep Deterministic Uncertainty: A Simple Baseline [arxiv2021] [Pytorch]
- Deep Deterministic Uncertainty for Semantic Segmentation [arxiv2021]
- On the Practicality of Deterministic Epistemic Uncertainty [arxiv2021]
- The Hidden Uncertainty in a Neural Network’s Activations [arxiv2020]
- A simple framework for uncertainty in contrastive learning [arxiv2020]
- Distance-based Confidence Score for Neural Network Classifiers [arxiv2017]
Conference
- Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression [CoRR2021]
- Training normalizing flows with the information bottleneck for competitive generative classification [NIPS2020]
- Simple and principled uncertainty estimation with deterministic deep learning via distance awareness [NIPS2020]
- Uncertainty Estimation Using a Single Deep Deterministic Neural Network [ICML2020] [Pytorch]
- Single-Model Uncertainties for Deep Learning [NIPS2019] [Pytorch]
- Sampling-Free Epistemic Uncertainty Estimation Using Approximated Variance Propagation [ICCV2019] [Pytorch]
Journal
- article
Arxiv
- Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors.[Arxiv2022]
- Testing for Outliers with Conformal p-values [arxiv2021] [python]
Conference
- Prediction Intervals: Split Normal Mixture from Quality-Driven Deep Ensembles [UAI2020] [Pytorch]
- Classification with Valid and Adaptive Coverage [NIPS2020]
- Conformal Prediction Under Covariate Shift [NIPS2019]
- Conformalized Quantile Regression [NIPS2019]
- Single-Model Uncertainties for Deep Learning [NIPS2019] [Pytorch]
- High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach [ICML2018] [Tensorflow]
Journal
- Exploring uncertainty in regression neural networks for construction of prediction intervals [Neurocomputing2022]
Arxiv
- Deep Deterministic Uncertainty for Semantic Segmentation [arxiv2021]
- Evaluating Bayesian Deep Learning Methods for Semantic Segmentation [arxiv2018]
Conference
- Robust Semantic Segmentation with Superpixel-Mix [BMVC2021]
- Classification with Valid and Adaptive Coverage [NIPS2020]
- DEAL: Difficulty-aware Active Learning for Semantic Segmentation [ACCV2020]
- Human Uncertainty Makes Classification More Robust [ICCV2019]
- Classification uncertainty of deep neural networks based on gradient information [IAPR Workshop2018]
- Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation [ICCV2019]
- Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation [MICCAI2019][Pytorch]
- A Probabilistic U-Net for Segmentation of Ambiguous Images [NIPS2018] [Pytorch]
- Evidential Deep Learning to Quantify Classification Uncertainty [NIPS2018] [Pytorch]
- Lightweight Probabilistic Deep Networks [CVPR2018][Pytorch]
- Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding [BMVC2017]
Journal
- Explainable machine learning in image classification models: An uncertainty quantification perspective." [KnowledgeBased2022]
Arxiv
- UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed TomographarXiv [arxiv2022]
- On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression [arxiv2022]
- Efficient Gaussian Neural Processes for Regression [arxiv2021]
- Evaluating and Calibrating Uncertainty Prediction in Regression Tasks [arxiv2020]
Conference
- Learning Structured Gaussians to Approximate Deep Ensembles [CVPR2022]
- Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate [AAAI2022]
- SLURP: Side Learning Uncertainty for Regression Problems [BMVC2021] [Pytorch]
- Learning to Predict Error for MRI Reconstruction [MICCAI2021]
- Deep Evidential Regression [NIPS2020] [Tensorflow]
- Well-Calibrated Regression Uncertainty in Medical Imaging with Deep Learning [MIDL2020] [Pytorch]
- On the uncertainty of self-supervised monocular depth estimation [CVPR2020] [Pytorch]
- Fast Uncertainty Estimation for Deep Learning Based Optical Flow [IROS2020]
- Inferring Distributions Over Depth from a Single Image [IROS2019] [Tensorflow]
- Multi-Task Learning based on Separable Formulation of Depth Estimation and its Uncertainty [CVPRW]
- Lightweight Probabilistic Deep Networks [CVPR2018][Pytorch]
- Uncertainty estimates and multi-hypotheses networks for optical flow [ECCV2018] [Tensorflow]
- Accurate Uncertainties for Deep Learning Using Calibrated Regression [ICML2018]
- Structured Uncertainty Prediction Networks [CVPR2018] [Tensorflow]
Journal
- Exploring uncertainty in regression neural networks for construction of prediction intervals [Neurocomputing2022]
- Calibrated Prediction Intervals for Neural Network Regressors [IEEE Access 2018][Python]
Arxiv
- Generalized out-of-distribution detection: A survey [arxiv2021]
- Towards Total Recall in Industrial Anomaly Detection [arxiv2021] [Pytorch]
- Do We Really Need to Learn Representations from In-domain Data for Outlier Detection? [arxiv2021]
- Exploring the Limits of Out-of-Distribution Detection [arxiv2021]
- DATE: Detecting Anomalies in Text via Self-Supervision of Transformers [arxiv2021]
- Frequentist uncertainty estimates for deep learning [arxiv2018]
Conference
- VOS: Learning What You Don't Know by Virtual Outlier Synthesis [ICLR2022] [Pytorch]
- Anomaly Detection via Reverse Distillation from One-Class Embedding [CVPR2022]
- Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection [WACV2022] [Pytorch]
- PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization [ICPR2020] [Pytorch]
- Detecting out-of-distribution image without learning from out-of-distribution data." [CVPR2020]
- Learning Open Set Network with Discriminative Reciprocal Points [ECCV2020]
- Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation [ECCV2020][Pytorch]
- Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection [ICCV2019] [Pytorch]
- Detecting the Unexpected via Image Resynthesis [ICCV2019][Pytorch]
Journal
- One Versus all for deep Neural Network for uncertaInty (OVNNI) quantification [IEEE Access2021]
- MUAD: Multiple Uncertainties for Autonomous Driving benchmark for multiple uncertainty types and tasks [arxiv2022]
- The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection [IJCV2021]
- Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning [arxiv2021][Tensorflow]
- Bayesian Torch [github]
- A Bayesian Neural Network library for PyTorch [github]
- Uncertainty Toolbox [github]
- Mixture Density Networks (MDN) for distribution and uncertainty estimation [github]
- Yarin Gal: BAYESIAN DEEP LEARNING 101 [website]
- MIT 6.S191: Evidential Deep Learning and Uncertainty (2021) [Youtube]
Awesome conformal prediction [github]