Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
Not on the map. Why?
Abstract (arXiv)
Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty. In current aleatoric uncertainty estimation frameworks, it is often neglected that the aleatoric uncertainty is an inherent attribute of the data and can only be correctly estimated with an unbiased oracle model. Since the oracle model is inaccessible in most cases, we propose a new sampling and selection strategy at train time to approximate the oracle model for aleatoric uncertainty estimation. Further, we show a trivial solution in the dual-head based heteroscedastic aleatoric uncertainty estimation framework and introduce a new uncertainty consistency loss to avoid it. For epistemic uncertainty estimation, we argue that the internal variable in a conditional latent variable model is another source of epistemic uncertainty to model the predictive distribution and explore the limited knowledge about the hidden true model. We validate our observation on a dense prediction task, i.e., camouflaged object detection. Our results show that our solution achieves both accurate deterministic results and reliable uncertainty estimation.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 85 references that are in the map. First posted on arXiv 22 Nov 2021.
Builds on
52 of 85 references.
References · 52
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
- 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
- 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
38 more
- 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
- 2017Advances in Variational Inferencecited by 236
- 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
- 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
- 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
- 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
- 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
- 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
- 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
- 2021Epistemic Neural Networkscited by 120
- 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
- 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 104
- 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
- 2020Masksembles for Uncertainty Estimationcited by 88
- 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
- 2020Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptationcited by 81
- 2018Lightweight Probabilistic Deep Networkscited by 77
- 2020SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimatescited by 75
- 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
- 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
- 2021Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regressioncited by 58
- 2020A statistical theory of cold posteriors in deep neural networkscited by 54
- 2020Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processescited by 43
- 2021Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertaintiescited by 41
- 2021Correlated Input-Dependent Label Noise in Large-Scale Image Classificationcited by 37
- 2020Multi-Loss Weighting with Coefficient of Variationscited by 36
- 2021Digging into Uncertainty in Self-supervised Multi-view Stereocited by 31
- 2021A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimationcited by 21
- 2020Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detectioncited by 18
- 2021Explaining Bayesian Neural Networkscited by 18
- 2015Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimizationcited by 17
- 2020D-LEMA: Deep Learning Ensembles from Multiple Annotations -- Application to Skin Lesion Segmentationcited by 16
- 2021Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancementcited by 15
- 2020Scalable Uncertainty for Computer Vision with Functional Variational Inferencecited by 12
- 2019Certainty Driven Consistency Loss on Multi-Teacher Networks for Semi-Supervised Learningcited by 11
- 2021A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Predictioncited by 10
- 2021Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertaintycited by 9
- 2021Bayesian Confidence Calibration for Epistemic Uncertainty Modellingcited by 5
50 most cited of 52 All 52 (JSON)
Built on by
Not cited yet.