What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

Abstract

There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty. We study models under the framework with per-pixel semantic segmentation and depth regression tasks. Further, our explicit uncertainty formulation leads to new loss functions for these tasks, which can be interpreted as learned attenuation. This makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.

NIPS 2017

References in corpus (2)

• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Depth Extraction from Video Using Non-parametric Sampling

Cited by in corpus (637)

• A Survey on Deep Learning in Medical Image Analysis
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• Recent advances and clinical applications of deep learning in medical image analysis
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
• Deep and Confident Prediction for Time Series at Uber
• Accurate Uncertainties for Deep Learning Using Calibrated Regression
• Predictive Uncertainty Estimation via Prior Networks
• Deep Ensembles: A Loss Landscape Perspective
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving
• Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles
• Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
• To Trust Or Not To Trust A Classifier
• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
• InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Reliable deep-learning-based phase imaging with uncertainty quantification
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Uncertainty and Interpretability in Convolutional Neural Networks for Semantic Segmentation of Colorectal Polyps
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization
• An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosis
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
• Simultaneous calibration of spectro-photometric distances and the Gaia DR2 parallax zero-point offset with deep learning
• Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
• Learned Cardinalities: Estimating Correlated Joins with Deep Learning
• Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations
• A Probabilistic U-Net for Segmentation of Ambiguous Images
• The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
• Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
• MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• DR$|$GRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images
• 3D Sketching using Multi-View Deep Volumetric Prediction
• StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
• Machine Learning Uncertainty as a Design Material: A Post-Phenomenological Inquiry
• Scalable agent alignment via reward modeling: a research direction
• Machine Learning and LHC Event Generation
• Multivariate Confidence Calibration for Object Detection
• A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects
• Addressing Failure Prediction by Learning Model Confidence
• A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence
• What Are Bayesian Neural Network Posteriors Really Like?
• Quantum Machine Learning: from physics to software engineering
• Bayesian deep learning for error estimation in the analysis of anomalous diffusion
• How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
• Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions
• What Do Compressed Deep Neural Networks Forget?
• Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms
• M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
• A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Understanding Event-Generation Networks via Uncertainties
• Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
• Event Generators for High-Energy Physics Experiments
• Bayesian convolutional neural network based MRI brain extraction on nonhuman primates
• A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
• SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
• Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
• Generative Networks for Precision Enthusiasts
• Confidence Measure Guided Single Image De-raining
• Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
• Multi-Task Learning of Height and Semantics from Aerial Images
• Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends
• Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
• Peeking Behind Objects: Layered Depth Prediction from a Single Image
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation
• Learning Functional Priors and Posteriors from Data and Physics
• Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference
• QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
• Detection of Face Recognition Adversarial Attacks
• Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning
• Uncertainty-Aware Organ Classification for Surgical Data Science Applications in Laparoscopy
• Modeling Uncertainty with Hedged Instance Embedding
• DPC-Net: Deep Pose Correction for Visual Localization
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• Leveraging Uncertainty Estimates for Predicting Segmentation Quality
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• Uncertainty for Identifying Open-Set Errors in Visual Object Detection
• An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
• Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with Bayesian inference for uncertainty-based quality-control
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation
• Discriminative out-of-distribution detection for semantic segmentation
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors
• Predictive Monitoring with Logic-Calibrated Uncertainty for Cyber-Physical Systems
• Optimal Uncertainty-guided Neural Network Training
• Active Learning with Partial Feedback
• Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
• Deep learning with self-supervision and uncertainty regularization to count fish in underwater images
• Two Invertible Networks for the Matrix Element Method
• Bounding Box Regression with Uncertainty for Accurate Object Detection
• Detection of 3D Bounding Boxes of Vehicles Using Perspective Transformation for Accurate Speed Measurement
• Mapping oil palm density at country scale: An active learning approach
• Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising
• Deep Active Learning for Named Entity Recognition
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• Embedded deep learning in ophthalmology: Making ophthalmic imaging smarter
• Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
• Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring
• Improving Semantic Segmentation via Video Propagation and Label Relaxation
• An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
• Hierarchical Consistency Regularized Mean Teacher for Semi-supervised 3D Left Atrium Segmentation
• Uncertainty-driven Sanity Check: Application to Postoperative Brain Tumor Cavity Segmentation
• Simple and Effective VAE Training with Calibrated Decoders
• GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays
• Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
• High-Quality Self-Supervised Deep Image Denoising
• Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors
• Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors
• D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
• Breaking baryon-cosmology degeneracy with the electron density power spectrum
• Deep Ensemble Analysis for Imaging X-ray Polarimetry
• Uncertainty-Aware Attention for Reliable Interpretation and Prediction
• Loss-Calibrated Approximate Inference in Bayesian Neural Networks
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Qualitative Analysis of Monte Carlo Dropout
• Using Deep Learning for Segmentation and Counting within Microscopy Data
• Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection
• Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples
• Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
• Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
• Parting with Illusions about Deep Active Learning
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
• Bayesian Autoencoders for Drift Detection in Industrial Environments
• Parameter Inference for Weak Lensing using Gaussian Processes and MOPED
• Returning CP-Observables to The Frames They Belong
• Uncertainty Quantification Metrics for Deep Regression
• Towards reliable head and neck cancers locoregional recurrence prediction using delta-radiomics and learning with rejection option
• Uncertainty-Aware Reliable Text Classification
• Organization of machine learning based product development as per ISO 26262 and ISO/PAS 21448
• Decentralized Bayesian Learning over Graphs
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
• ProbAct: A Probabilistic Activation Function for Deep Neural Networks
• Bayesian Neural Network Priors Revisited
• TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation
• Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
• AANet: Attribute Attention Network for Person Re-Identifications
• Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables
• Cleaning our own Dust: Simulating and Separating Galactic Dust Foregrounds with Neural Networks
• Regularizing Deep Networks with Semantic Data Augmentation
• Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting
• Bayesian Neural Networks With Maximum Mean Discrepancy Regularization
• Deep learning for intensity mapping observations: Component extraction
• Curious iLQR: Resolving Uncertainty in Model-based RL
• All You Need is a Good Functional Prior for Bayesian Deep Learning
• Volumetric Occupancy Mapping With Probabilistic Depth Completion for Robotic Navigation
• Giving Commands to a Self-Driving Car: How to Deal with Uncertain Situations?
• Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
• Semi-supervised Left Atrium Segmentation with Mutual Consistency Training
• Overcome the Fear Of Missing Out: Active Sensing UAV Scanning for Precision Agriculture
• Inhibited Softmax for Uncertainty Estimation in Neural Networks
• Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions
• Restructuring TCAD System: Teaching Traditional TCAD New Tricks
• Deep Learning Through the Lens of Example Difficulty
• A Less Biased Evaluation of Out-of-distribution Sample Detectors
• STUaNet: Understanding uncertainty in spatiotemporal collective human mobility
• Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes
• Safe end-to-end imitation learning for model predictive control
• View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
• Modality Attention and Sampling Enables Deep Learning with Heterogeneous Marker Combinations in Fluorescence Microscopy
• BNNpriors: A library for Bayesian neural network inference with different prior distributions
• Calibrating Uncertainties in Object Localization Task
• On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation
• Trajectory Planning Under Environmental Uncertainty With Finite-Sample Safety Guarantees
• Learning a Deep ConvNet for Multi-label Classification with Partial Labels
• Disentangled High Quality Salient Object Detection
• How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• NPBDREG: Uncertainty Assessment in Diffeomorphic Brain MRI Registration using a Non-parametric Bayesian Deep-Learning Based Approach
• A Bayesian Deep Learning Approach to Near-Term Climate Prediction
• Multi-modal Ensemble Classification for Generalized Zero Shot Learning
• System Theoretic View on Uncertainties
• From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
• How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks
• Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification
• Active Testing: Sample-Efficient Model Evaluation
• Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
• Deep Multi-View Stereo gone wild
• Bayesian Inference for Large Scale Image Classification
• Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
• Can We Leverage Predictive Uncertainty to Detect Dataset Shift and Adversarial Examples in Android Malware Detection?
• ClusterFusion: Leveraging Radar Spatial Features for Radar-Camera 3D Object Detection in Autonomous Vehicles
• Unsupervised Knowledge-Transfer for Learned Image Reconstruction
• Predicting Model Failure using Saliency Maps in Autonomous Driving Systems
• Supervised Uncertainty Quantification for Segmentation with Multiple Annotations
• Spatial Uncertainty Sampling for End-to-End Control
• Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts
• ProtoAttend: Attention-Based Prototypical Learning
• Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
• Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes
• Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs
• Quantifying Uncertainties in Natural Language Processing Tasks
• Deep Network Uncertainty Maps for Indoor Navigation
• Calibrating Deep Convolutional Gaussian Processes
• A Mathematical Analysis of Learning Loss for Active Learning in Regression
• A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentation
• Objects are Different: Flexible Monocular 3D Object Detection
• CRUDE: Calibrating Regression Uncertainty Distributions Empirically
• Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
• EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation
• Reliable training and estimation of variance networks
• LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
• Probabilistic Metamodels for an Efficient Characterization of Complex Driving Scenarios
• Self-supervised Remote Sensing Images Change Detection at Pixel-level
• Pitfalls in Machine Learning Research: Reexamining the Development Cycle
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
• Deep Deterministic Uncertainty for Semantic Segmentation
• Attention-based Multi-fidelity Machine Learning Model for Computational Fractional Flow Reserve Assessment
• Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions
• Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• Hypergraph Learning for Identification of COVID-19 with CT Imaging
• Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction
• EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking
• A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy
• Simultaneous lesion and neuroanatomy segmentation in Multiple Sclerosis using deep neural networks
• PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction
• The Hidden Uncertainty in a Neural Networks Activations
• A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
• Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method
• Diversity inducing Information Bottleneck in Model Ensembles
• Evaluating Object (mis)Detection from a Safety and Reliability Perspective: Discussion and Measures
• Self-tuning moving horizon estimation of nonlinear systems via physics-informed machine learning Koopman modeling
• Automated Olfactory Bulb Segmentation on High Resolutional T2-Weighted MRI
• Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
• Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
• Deep Evidential Regression
• Visual Odometry Revisited: What Should Be Learnt?
• Towards calibrated and scalable uncertainty representations for neural networks
• Example Forgetting: A Novel Approach to Explain and Interpret Deep Neural Networks in Seismic Interpretation
• Calibration of Model Uncertainty for Dropout Variational Inference
• Bayesian Neural Networks for Reversible Steganography
• Cold Posteriors and Aleatoric Uncertainty
• Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections
• Robust Representation Learning with Feedback for Single Image Deraining
• Bayesian active learning for production, a systematic study and a reusable library
• Dense Uncertainty Estimation
• Evidential Deep Learning for Open Set Action Recognition
• Certification of embedded systems based on Machine Learning: A survey
• Backward-Compatible Prediction Updates: A Probabilistic Approach
• Quantifying sources of uncertainty in drug discovery predictions with probabilistic models
• Explaining Deep Models through Forgettable Learning Dynamics
• Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression
• Deep Bayesian ICP Covariance Estimation
• Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks
• A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks
• Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums
• Data-Driven Random Access Optimization in Multi-Cell IoT Networks with NOMA
• Interval Neural Networks: Uncertainty Scores
• Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
• Angular Visual Hardness
• The PAU Survey: Background light estimation with deep learning techniques
• A Marauder's Map of Security and Privacy in Machine Learning
• ENG: End-to-end Neural Geometry for Robust Depth and Pose Estimation using CNNs
• Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
• Visualization of Convolutional Neural Networks for Monocular Depth Estimation
• Improving Back-Translation with Uncertainty-based Confidence Estimation
• A Financial Service Chatbot based on Deep Bidirectional Transformers
• SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
• Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
• Distribution-free binary classification: prediction sets, confidence intervals and calibration
• Integrating Uncertainty into Neural Network-based Speech Enhancement
• Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map Prediction
• How Do Neural Networks Estimate Optical Flow? A Neuropsychology-Inspired Study
• MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
• Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictions
• Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex
• Data Uncertainty Learning in Face Recognition
• DistFL: Distribution-aware Federated Learning for Mobile Scenarios
• Adaptive Adversarial Attack on Scene Text Recognition
• Constraining cosmological parameters from N-body simulations with Variational Bayesian Neural Networks
• Multitask Learning in Minimally Invasive Surgical Vision: A Review
• Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement
• Confidence-Calibrated Face and Kinship Verification
• Deep density networks and uncertainty in recommender systems
• Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reduction
• Neural Processes Mixed-Effect Models for Deep Normative Modeling of Clinical Neuroimaging Data
• Engineering Reliable Deep Learning Systems
• Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
• Uncertainty-Aware Self-supervised Neural Network for Liver $T_{1\rho }$ Mapping with Relaxation Constraint
• Change-point detection in anomalous-diffusion trajectories utilising machine-learning-based uncertainty estimates
• Concept-Oriented Deep Learning: Generative Concept Representations
• Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation
• Universal uncertainty estimation for nuclear detector signals with neural networks and ensemble learning
• Accurate Surrogate Amplitudes with Calibrated Uncertainties
• Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
• Uncertainty-Encoded Multi-Modal Fusion for Robust Object Detection in Autonomous Driving
• Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors
• Attending to Discriminative Certainty for Domain Adaptation
• Robust Semantic Segmentation with Ladder-DenseNet Models
• Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
• Revisiting the Evaluation of Uncertainty Estimation and Its Application to Explore Model Complexity-Uncertainty Trade-Off
• Learning Representations for Predicting Future Activities
• Pedestrian Wind Factor Estimation in Complex Urban Environments
• LiBRe: A Practical Bayesian Approach to Adversarial Detection
• An Unbiased Estimator of the Full-sky CMB Angular Power Spectrum at Large Scales using Neural Networks
• Dynamical masses across the Hertzsprung-Russell diagram
• Multi-Objective Optimization Under Uncertainty of Part Quality in Fused Filament Fabrication
• Learning Probabilistic Coordinate Fields for Robust Correspondences
• Self-supervised Learning for Single View Depth and Surface Normal Estimation
• Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks
• MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation
• VFunc: a Deep Generative Model for Functions
• Scalable Multi-Task Gaussian Process Tensor Regression for Normative Modeling of Structured Variation in Neuroimaging Data
• Large-scale Heteroscedastic Regression via Gaussian Process
• Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet
• Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes
• Quantifying Intrinsic Uncertainty in Classification via Deep Dirichlet Mixture Networks
• Uncertainty-based graph convolutional networks for organ segmentation refinement
• Dangers of Bayesian Model Averaging under Covariate Shift
• Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting
• Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals
• Compromise-free Bayesian neural networks
• To Trust or Not to Trust a Regressor: Estimating and Explaining Trustworthiness of Regression Predictions
• Noisy Batch Active Learning with Deterministic Annealing
• Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction
• Training VAEs Under Structured Residuals
• Vision-Based Uncertainty-Aware Motion Planning based on Probabilistic Semantic Segmentation
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration
• Robust Semantic Segmentation with Superpixel-Mix
• Informed MCMC with Bayesian Neural Networks for Facial Image Analysis
• Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction
• Theoretical characterization of uncertainty in high-dimensional linear classification
• Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss
• Experimental design for MRI by greedy policy search
• Few-shot brain segmentation from weakly labeled data with deep heteroscedastic multi-task networks
• Fast and Reliable Probabilistic Face Embeddings in the Wild
• Uncertainty-Aware Deep Calibrated Salient Object Detection
• Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network
• Non-local Recurrent Regularization Networks for Multi-view Stereo
• Deep Learning reconstruction with uncertainty estimation for $\gamma$ photon interaction in fast scintillator detectors
• No One Representation to Rule Them All: Overlapping Features of Training Methods
• Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
• Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning
• Characteristics of Monte Carlo Dropout in Wide Neural Networks
• Uncertainty Prediction for Deep Sequential Regression Using Meta Models
• Aggregating explanation methods for stable and robust explainability
• Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning
• Gibbs Sampling the Posterior of Neural Networks
• Single-Modal Entropy based Active Learning for Visual Question Answering
• Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
• Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion
• Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
• Tractable Approximate Gaussian Inference for Bayesian Neural Networks
• Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalized Musculoskeletal Modeling
• Astronomical Image Quality Prediction based on Environmental and Telescope Operating Conditions
• Impact of individual rater style on deep learning uncertainty in medical imaging segmentation
• NOMU: Neural Optimization-based Model Uncertainty
• Continual Learning Using Bayesian Neural Networks
• Neural Identification for Control
• Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks
• IntraSeismic: a coordinate-based learning approach to seismic inversion
• A Priori Uncertainty Quantification of Reacting Turbulence Closure Models using Bayesian Neural Networks
• Measuring the Substructure Mass Power Spectrum of 23 SLACS Strong Galaxy-Galaxy Lenses with Convolutional Neural Networks
• Generative Unfolding with Distribution Mapping
• Scalar is Not Enough: Vectorization-based Unbiased Learning to Rank
• Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
• Initialisation of Autonomous Aircraft Visual Inspection Systems via CNN-Based Camera Pose Estimation
• SLURP: Side Learning Uncertainty for Regression Problems
• Quantification of Uncertainties in Deep Learning-based Environment Perception
• Confidence-Guided Learning Process for Continuous Classification of Time Series
• Uncertainty-Aware Multi-View Representation Learning
• Learning to Map for Active Semantic Goal Navigation
• Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images
• Bayesian OOD detection with aleatoric uncertainty and outlier exposure
• Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulations
• A Decoupled Uncertainty Model for MRI Segmentation Quality Estimation
• Improving Robustness of Deep Neural Networks for Aerial Navigation by Incorporating Input Uncertainty
• A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers
• Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation
• On Batch Normalisation for Approximate Bayesian Inference
• Pushing the Envelope of Thin Crack Detection
• View-Invariant Probabilistic Embedding for Human Pose
• Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
• Analyzing Epistemic and Aleatoric Uncertainty for Drusen Segmentation in Optical Coherence Tomography Images
• Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets
• A Confidence-Calibrated MOBA Game Winner Predictor
• Labels Are Not Perfect: Improving Probabilistic Object Detection via Label Uncertainty
• Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learning
• Synthetic Perfusion Maps: Imaging Perfusion Deficits in DSC-MRI with Deep Learning
• Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
• Improving Confidence Estimates for Unfamiliar Examples
• PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction
• Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization
• A Mapping of Assurance Techniques for Learning Enabled Autonomous Systems to the Systems Engineering Lifecycle
• Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
• Prediction intervals for Deep Neural Networks
• Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
• Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
• DREAMS: A python framework for Training Deep Learning Models on EEG Data with Model Card Reporting for Medical Applications
• Evaluating subgroup disparity using epistemic uncertainty in mammography
• Uncertainty Estimation in Cancer Survival Prediction
• Continuity of Generalized Entropy and Statistical Learning
• Bayesian Learning of Probabilistic Dipole Inversion for Quantitative Susceptibility Mapping
• Uncertainty-driven ensembles of deep architectures for multiclass classification. Application to COVID-19 diagnosis in chest X-ray images
• Epistemic Neural Networks
• Effect of latent space distribution on the segmentation of images with multiple annotations
• Modeling the Uncertainty in Electronic Health Records: a Bayesian Deep Learning Approach
• Left Ventricle Segmentation and Quantification from Cardiac Cine MR Images via Multi-task Learning
• Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals
• MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving
• O2D2: Out-Of-Distribution Detector to Capture Undecidable Trials in Authorship Verification
• Sparse Uncertainty Representation in Deep Learning with Inducing Weights
• Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection
• Joint Learning of Semantic Alignment and Object Landmark Detection
• Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective
• Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss
• Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction
• Insights into Fairness through Trust: Multi-scale Trust Quantification for Financial Deep Learning
• Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective
• Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
• Image segmentation of liver stage malaria infection with spatial uncertainty sampling
• Estimation with Uncertainty via Conditional Generative Adversarial Networks
• Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts
• OFEI: A Semi-black-box Android Adversarial Sample Attack Framework Against DLaaS
• Generating and Exploiting Probabilistic Monocular Depth Estimates
• Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning
• UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation
• SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation
• BDNNSurv: Bayesian deep neural networks for survival analysis using pseudo values
• Application-driven Validation of Posteriors in Inverse Problems
• A Novel Regression Loss for Non-Parametric Uncertainty Optimization
• Information-Theoretic Odometry Learning
• Approaching Neural Network Uncertainty Realism
• Uncertainty quantification of molecular property prediction using Bayesian neural network models
• Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations
• Probabilistic Discriminative Learning with Layered Graphical Models
• Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time
• Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
• Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas
• Efficient Action Recognition Using Confidence Distillation
• Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization
• It Is Likely That Your Loss Should be a Likelihood
• Weakly- and Semi-Supervised Probabilistic Segmentation and Quantification of Ultrasound Needle-Reverberation Artifacts to Allow Better AI Understanding of Tissue Beneath Needles
• Uncertainty-Aware Self-Supervised Target-Mass Grasping of Granular Foods
• Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
• Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
• Risk-Aware Planning by Confidence Estimation using Deep Learning-Based Perception
• Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization
• An Alarm System For Segmentation Algorithm Based On Shape Model
• Learning Risk-aware Costmaps for Traversability in Challenging Environments
• Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
• Towards Better Performance and More Explainable Uncertainty for 3D Object Detection of Autonomous Vehicles
• Uncertainty-aware Remaining Useful Life predictor
• Non-Parametric Calibration for Classification
• Quantile Surfaces -- Generalizing Quantile Regression to Multivariate Targets
• Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
• Inferring Distributions Over Depth from a Single Image
• Probabilistic Oriented Object Detection in Automotive Radar
• Adversarially Learned Mixture Model
• Extrapolating Jet Radiation with Autoregressive Transformers
• CheXbreak: Misclassification Identification for Deep Learning Models Interpreting Chest X-rays
• Robustness via Cross-Domain Ensembles
• Deep Metric Learning for Open World Semantic Segmentation
• What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
• Efficient Uncertainty Estimation for Semantic Segmentation in Videos
• Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables
• Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
• Understanding the Under-Coverage Bias in Uncertainty Estimation
• Active Learning in CNNs via Expected Improvement Maximization
• Ex uno plures: Splitting One Model into an Ensemble of Subnetworks
• On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra-observer Variability in 2D Echocardiography Quality Assessment
• Joint Spatial and Layer Attention for Convolutional Networks
• Uncertainty-Aware Semantic Augmentation for Neural Machine Translation
• Explanation and Use of Uncertainty Quantified by Bayesian Neural Network Classifiers for Breast Histopathology Images
• Uncertainty-Aware Few-Shot Image Classification
• Deep Momentum Uncertainty Hashing
• Uncertainty-Based Biological Age Estimation of Brain MRI Scans
• Global Voxel Transformer Networks for Augmented Microscopy
• Estimating MRI Image Quality via Image Reconstruction Uncertainty
• Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
• Calibrated Prediction Intervals for Neural Network Regressors
• Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation
• The role of MRI physics in brain segmentation CNNs: achieving acquisition invariance and instructive uncertainties
• Deep Multi-view Depth Estimation with Predicted Uncertainty
• Novel Uncertainty Framework for Deep Learning Ensembles
• Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural Networks
• Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?
• Probabilistic Safety for Bayesian Neural Networks
• Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty
• Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning
• Dependency Decomposition and a Reject Option for Explainable Models
• Multi-Fingered Grasp Planning via Inference in Deep Neural Networks
• Close-Proximity Underwater Terrain Mapping Using Learning-based Coarse Range Estimation
• Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification
• Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
• Uncertainty-aware Sensitivity Analysis Using Rényi Divergences
• RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection
• Learning Resilient Behaviors for Navigation Under Uncertainty
• Uncertainty-aware Generalized Adaptive CycleGAN
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models
• Uncertainty-aware INVASE: Enhanced Breast Cancer Diagnosis Feature Selection
• Bayesian Neural Tree Models for Nonparametric Regression
• Accurate and Reliable Forecasting using Stochastic Differential Equations
• Adversarial View-Consistent Learning for Monocular Depth Estimation
• Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty
• A Bayesian Convolutional Neural Network for Robust Galaxy Ellipticity Regression
• Physical Cue based Depth-Sensing by Color Coding with Deaberration Network
• Parameters Estimation from the 21 cm signal using Variational Inference
• Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
• Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing
• Perceptual Attention-based Predictive Control
• Deep covariate-learning: optimising information extraction from terrain texture for geostatistical modelling applications
• Looking at the posterior: accuracy and uncertainty of neural-network predictions
• Certainty Driven Consistency Loss on Multi-Teacher Networks for Semi-Supervised Learning
• Prime-Aware Adaptive Distillation
• Learning Stereo Matchability in Disparity Regression Networks
• Uncertainty Propagation in Node Classification
• Boundary Uncertainty in a Single-Stage Temporal Action Localization Network
• Quantifying Epistemic Uncertainty in Deep Learning
• MCU-Net: A framework towards uncertainty representations for decision support system patient referrals in healthcare contexts
• Bayesian deep learning for mapping via auxiliary information: a new era for geostatistics?
• Confidence Inference for Focused Learning in Stereo Matching
• Diagnostics in Semantic Segmentation
• That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentation
• Generalized Learning with Rejection for Classification and Regression Problems
• Dirichlet uncertainty wrappers for actionable algorithm accuracy accountability and auditability
• Probabilistic Approach for Road-Users Detection
• Multichannel Semantic Segmentation with Unsupervised Domain Adaptation
• Quantification of Predictive Uncertainty via Inference-Time Sampling
• Prb-GAN: A Probabilistic Framework for GAN Modelling
• Depth by Poking: Learning to Estimate Depth from Self-Supervised Grasping
• Generative Parameter Sampler For Scalable Uncertainty Quantification
• Probabilistic Spatial Analysis in Quantitative Microscopy with Uncertainty-Aware Cell Detection using Deep Bayesian Regression of Density Maps
• Probabilistic Human Motion Prediction via A Bayesian Neural Network
• Improving Uncertainty Calibration via Prior Augmented Data
• Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint
• Unsupervised Local Discrimination for Medical Images
• Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
• Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
• Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
• A Bayesian Neural Network based on Dropout Regulation
• Exploring ensembles and uncertainty minimization in denoising networks
• Exploring Temporal Information for Improved Video Understanding
• A deep learning pipeline for localization, differentiation, and uncertainty estimation of liver lesions using multi-phasic and multi-sequence MRI
• Privacy Preserving Recalibration under Domain Shift
• Deep Classifiers with Label Noise Modeling and Distance Awareness
• Bayesian Deep Learning Hyperparameter Search for Robust Function Mapping to Polynomials with Noise
• Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data
• CogSense: A Cognitively Inspired Framework for Perception Adaptation
• $f$-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
• Modulating Scalable Gaussian Processes for Expressive Statistical Learning
• Hierarchical Recurrent Filtering for Fully Convolutional DenseNets
• Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation
• T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation
• Automatic Segmentation of Gross Target Volume of Nasopharynx Cancer using Ensemble of Multiscale Deep Neural Networks with Spatial Attention
• Handwriting Prediction Considering Inter-Class Bifurcation Structures
• Active Learning for Bayesian 3D Hand Pose Estimation
• Learning to Predict Error for MRI Reconstruction
• Improving Building Segmentation for Off-Nadir Satellite Imagery
• Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery Workflows
• Risk-Aware Reasoning for Autonomous Vehicles
• Exploring Instance-Level Uncertainty for Medical Detection
• Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?
• Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
• A General Divergence Modeling Strategy for Salient Object Detection
• MIMIR: Deep Regression for Automated Analysis of UK Biobank Body MRI
• DeepSemanticHPPC: Hypothesis-based Planning over Uncertain Semantic Point Clouds
• PANDA: A Gigapixel-level Human-centric Video Dataset
• Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
• Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties
• Lightweight Data Fusion with Conjugate Mappings
• On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey
• Multivariate Deep Evidential Regression
• Estimating localized complexity of white-matter wiring with GANs
• Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
• Signed Input Regularization
• The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals
• Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation
• Uncertainty estimation under model misspecification in neural network regression
• Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Data
• Predicting Gene Expression Between Species with Neural Networks
• Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes
• Deep Learning Meets SAR
• Training BatchNorm Only in Neural Architecture Search and Beyond
• Xi-Vector Embedding for Speaker Recognition
• A Simple Framework to Quantify Different Types of Uncertainty in Deep Neural Networks for Image Classification
• A Research Agenda on Pediatric Chest X-Ray: Is Deep Learning Still in Childhood?
• Fundamental Issues Regarding Uncertainties in Artificial Neural Networks
• A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation
• MACEst: The reliable and trustworthy Model Agnostic Confidence Estimator
• Predicting Critical Biogeochemistry of the Southern Ocean for Climate Monitoring
• Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain
• Perceptual Consistency in Video Segmentation
• Sequential Learning of Visual Tracking and Mapping Using Unsupervised Deep Neural Networks
• Robustness via Uncertainty-aware Cycle Consistency
• Adversarial Structure Matching for Structured Prediction Tasks
• Learning joint lesion and tissue segmentation from task-specific hetero-modal datasets
• Active Learning for UAV-based Semantic Mapping
• Calibration and Uncertainty Quantification of Bayesian Convolutional Neural Networks for Geophysical Applications
• Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers
• Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training Samples
• Classifying different types of solar wind plasma with uncertainty estimations using machine learning
• Uncertainty Surrogates for Deep Learning
• A Front-End for Dense Monocular SLAM using a Learned Outlier Mask Prior
• Deep Probabilistic Feature-metric Tracking
• n-MeRCI: A new Metric to Evaluate the Correlation Between Predictive Uncertainty and True Error
• Multi-view Alignment and Generation in CCA via Consistent Latent Encoding
• Machine-learning enables Image Reconstruction and Classification in a "see-through" camera
• Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging
• Predicting Human Trajectories by Learning and Matching Patterns
• Permutation invariance and uncertainty in multitemporal image super-resolution
• Understanding Uncertainty of Edge Computing: New Principle and Design Approach
• Informative sample generation using class aware generative adversarial networks for classification of chest Xrays
• Implications of Human Irrationality for Reinforcement Learning
• A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehicles
• Estimating the Uncertainty of Neural Network Forecasts for Influenza Prevalence Using Web Search Activity
• Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor
• Interval Deep Learning for Uncertainty Quantification in Safety Applications
• Sampling possible reconstructions of undersampled acquisitions in MR imaging