mlsanityData to 7 Oct 2026

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

arXiv 2207.06873 ↗First posted 14 Jul 2022cs.CV cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

High-quality calibrated uncertainty estimates are crucial for numerous real-world applications, especially for deep learning-based deployed ML systems. While Bayesian deep learning techniques allow uncertainty estimation, training them with large-scale datasets is an expensive process that does not always yield models competitive with non-Bayesian counterparts. Moreover, many of the high-performing deep learning models that are already trained and deployed are non-Bayesian in nature and do not provide uncertainty estimates. To address these issues, we propose BayesCap that learns a Bayesian identity mapping for the frozen model, allowing uncertainty estimation. BayesCap is a memory-efficient method that can be trained on a small fraction of the original dataset, enhancing pretrained non-Bayesian computer vision models by providing calibrated uncertainty estimates for the predictions without (i) hampering the performance of the model and (ii) the need for expensive retraining the model from scratch. The proposed method is agnostic to various architectures and tasks. We show the efficacy of our method on a wide variety of tasks with a diverse set of architectures, including image super-resolution, deblurring, inpainting, and crucial application such as medical image translation. Moreover, we apply the derived uncertainty estimates to detect out-of-distribution samples in critical scenarios like depth estimation in autonomous driving. Code is available at https://github.com/ExplainableML/BayesCap.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 55 of its 84 references that are in the map. First posted on arXiv 14 Jul 2022.

Builds on

55 of 84 references.

References · 55

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  9. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  10. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  11. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  12. 2016Colorful Image Colorizationcited by 1,113
38 more
  1. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  2. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  3. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  4. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  5. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  6. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  7. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  8. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  9. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  10. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  11. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  12. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  13. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  14. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  15. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  16. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  17. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  18. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  19. 2020Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learningcited by 190
  20. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  21. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 166
  22. 2018IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environmentscited by 163
  23. 2019Practical Deep Learning with Bayesian Principlescited by 158
  24. 2018MedGAN: Medical Image Translation using GANscited by 152
  25. 2019Deep Learning on Image Denoising: An overviewcited by 128
  26. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  27. 2018Distribution Matching Losses Can Hallucinate Features in Medical Image Translationcited by 99
  28. 2019Evaluating and Calibrating Uncertainty Prediction in Regression Taskscited by 85
  29. 2020Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantificationcited by 77
  30. 2018Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Controlcited by 54
  31. 2019Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inferencecited by 35
  32. 2021Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learningcited by 25
  33. 2020Calibration of Model Uncertainty for Dropout Variational Inferencecited by 18
  34. 2021Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Datacited by 18
  35. 2021Bayesian OOD detection with aleatoric uncertainty and outlier exposurecited by 16
  36. 2021Uncertainty-Guided Progressive GANs for Medical Image Translationcited by 16
  37. 2021Robustness via Uncertainty-aware Cycle Consistencycited by 16
  38. 2019Robust Super-Resolution GAN, with Manifold-based and Perception Losscited by 15

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 2; 2025: 7; 2026: 3.

23 papers.

Sort:

By area:

  1. 2023Uncertainty-inspired Open Set Learning for Retinal Anomaly Identificationcited by 18
  2. 2023Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural Networkscited by 14
  3. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  4. 2024Revisiting Confidence Estimation: Towards Reliable Failure Predictioncited by 9
  5. 2023ProbVLM: Probabilistic Adapter for Frozen Vision-Language Modelscited by 7
  6. 2023Out-of-Distribution Detection for Monocular Depth Estimationcited by 7
  7. 2023Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regressioncited by 7
  8. 2023On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentationcited by 6
  9. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 5
  10. 2023USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolutioncited by 4
  11. 2023Likelihood Annealing: Fast Calibrated Uncertainty for Regressioncited by 3
  12. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
11 more
  1. 2025Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysiscited by 2
  2. 2023An Uncertainty Aided Framework for Learning based Liver T1ρ Mapping and Analysiscited by 1
  3. 2023HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiogramscited by 1
  4. 2025BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolutioncited by 1
  5. 2026Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restorationcited by 1
  6. 2023Uncertainty-Driven Multi-Scale Feature Fusion Network for Real-time Image Derainingcited by 0
  7. 2025Are you SURE? Enhancing Multimodal Pretraining with Missing Modalities through Uncertainty Estimationcited by 0
  8. 2025Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networkscited by 0
  9. 2025Uncertainty-aware Test-Time Training (UT3) for Efficient On-the-fly Domain Adaptive Dense Regressioncited by 0
  10. 2026CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Modelcited by 0
  11. 2026Explainable Uncertainty Estimation for Reliable Medical AIcited by 0