mlsanityData to 7 Oct 2026

Enabling Uncertainty Estimation in Iterative Neural Networks

arXiv 2403.16732 ↗First posted 25 Mar 2024cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of their successive outputs is highly correlated with the accuracy of the value to which they converge. Thus, we can use the convergence rate as a useful proxy for uncertainty. This results in an approach to uncertainty estimation that provides state-of-the-art estimates at a much lower computational cost than techniques like Ensembles, and without requiring any modifications to the original iterative model. We demonstrate its practical value by embedding it in two application domains: road detection in aerial images and the estimation of aerodynamic properties of 2D and 3D shapes.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 46 of its 85 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

46 of 85 references.

References · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2018Neural Ordinary Differential Equationscited by 3,733
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  9. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  10. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  11. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  12. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
34 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  2. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  3. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  4. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  5. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 438
  6. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
  7. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  8. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  9. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  10. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  11. 2019Topology-Preserving Deep Image Segmentationcited by 198
  12. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  13. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  14. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  15. 2020MeshSDF: Differentiable Iso-Surface Extractioncited by 112
  16. 2018RoadTracer: Automatic Extraction of Road Networks from Aerial Imagescited by 102
  17. 2020Masksembles for Uncertainty Estimationcited by 88
  18. 2020Bayesian Deep Learning via Subnetwork Inferencecited by 85
  19. 2017Beyond the Pixel-Wise Loss for Topology-Aware Delineationcited by 82
  20. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  21. 2017On weight initialization in deep neural networkscited by 67
  22. 2020Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flowscited by 60
  23. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  24. 2020Depth Uncertainty in Neural Networkscited by 56
  25. 2017Improving the Expected Improvement Algorithmcited by 54
  26. 2018Geodesic Convolutional Shape Optimizationcited by 37
  27. 2019Recurrent U-Net for Resource-Constrained Segmentationcited by 27
  28. 2021Deep Deterministic Uncertainty for Semantic Segmentationcited by 24
  29. 2020Promoting Connectivity of Network-Like Structures by Enforcing Region Separationcited by 19
  30. 2022ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inferencecited by 15
  31. 2018Double Refinement Network for Efficient Indoor Monocular Depth Estimationcited by 5
  32. 2017Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detectioncited by 4
  33. 2022PartAL: Efficient Partial Active Learning in Multi-Task Visual Settingscited by 3
  34. 2021Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineatecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 3; 2026: 1.

11 papers.

  1. 2024MirrorCheck: Efficient Adversarial Defense for Vision-Language Modelscited by 19
  2. 2024Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifiercited by 12
  3. 2024Assessing Sample Quality via the Latent Space of Generative Modelscited by 8
  4. 2024IT3: Idempotent Test-Time Trainingcited by 6
  5. 2024Shadow Removal Refinement via Material-Consistent Shadow Edgescited by 5
  6. 2024Uncertainty Estimation for 3D Object Detection via Evidential Learningcited by 5
  7. 2024Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentationcited by 2
  8. 2025High Resolution UDF Meshing via Iterative Networkscited by 2
  9. 2025CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentationcited by 1
  10. 2025C(NN)FD -- Deep Learning Modelling of Multi-Stage Axial Compressors Aerodynamicscited by 0
  11. 2026Uncertainty Quantification in Federated Granger Causality Learningcited by 0