mlsanityData to 7 Oct 2026

Pretrained Visual Uncertainties

arXiv 2402.16569 ↗First posted 26 Feb 2024cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Accurate uncertainty estimation is vital to trustworthy machine learning, yet uncertainties typically have to be learned for each task anew. This work introduces the first pretrained uncertainty modules for vision models. Similar to standard pretraining this enables the zero-shot transfer of uncertainties learned on a large pretraining dataset to specialized downstream datasets. We enable our large-scale pretraining on ImageNet-21k by solving a gradient conflict in previous uncertainty modules and accelerating the training by up to 180x. We find that the pretrained uncertainties generalize to unseen datasets. In scrutinizing the learned uncertainties, we find that they capture aleatoric uncertainty, disentangled from epistemic components. We demonstrate that this enables safe retrieval and uncertainty-aware dataset visualization. To encourage applications to further problems and domains, we release all pretrained checkpoints and code under https://github.com/mkirchhof/url .

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 26 Feb 2024.

Builds on

32 of 54 references.

References · 32

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  4. 2013Describing Textures in the Wildcited by 2,110
  5. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  6. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  7. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  8. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  9. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  10. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  11. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 419
  12. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
20 more
  1. 2024The Faiss librarycited by 370
  2. 2019Learning Loss for Active Learningcited by 335
  3. 2020Are we done with ImageNet?cited by 329
  4. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  5. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  6. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  7. 2023Probabilistic Concept Bottleneck Modelscited by 101
  8. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  9. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  10. 2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43
  11. 2023Improved Probabilistic Image-Text Representationscited by 40
  12. 2023What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifierscited by 35
  13. 2023A framework for benchmarking class-out-of-distribution detection and its application to ImageNetcited by 31
  14. 2023Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputscited by 28
  15. 2022Representation Uncertainty in Self-Supervised Learning as Variational Inferencecited by 22
  16. 2022A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learningcited by 19
  17. 2023URL: A Representation Learning Benchmark for Transferable Uncertainty Estimatescited by 17
  18. 2023Learning Sample Difficulty from Pre-trained Models for Reliable Predictioncited by 15
  19. 2023Massively Scaling Heteroscedastic Classifierscited by 11
  20. 2022Probabilistic Embeddings Revisitedcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 2.

10 papers.

  1. 2024Scoring Rules and Calibration for Imprecise Probabilitiescited by 10
  2. 2025ViLU: Learning Vision-Language Uncertainties for Failure Predictioncited by 9
  3. 2025Three Types of Calibration with Properties and their Semantic and Formal Relationshipscited by 5
  4. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
  5. 2026Uncertainty Quantification for LLM Function-Callingcited by 2
  6. 2024Uncertainties of Latent Representations in Computer Visioncited by 1
  7. 2024Open-Set Semantic Uncertainty Aware Metric-Semantic Graph Matchingcited by 1
  8. 2025On the Generalization of Representation Uncertainty in Earth Observationcited by 1
  9. 2025Collision Risk Estimation via Loss Prediction in End-to-End Autonomous Drivingcited by 1
  10. 2026Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learningcited by 0