# Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models

arXiv: https://arxiv.org/abs/2406.18580 · HTML: https://mlsanity.com/paper/2406.18580/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts](https://mlsanity.com/paper/2006.09239/) (2020)
- [Estimating Mixture Entropy with Pairwise Distances](https://mlsanity.com/paper/1706.02419/) (2017)
- [Synthetic Medical Images from Dual Generative Adversarial Networks](https://mlsanity.com/paper/1709.01872/) (2017)
- [Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions](https://mlsanity.com/paper/2105.04471/) (2021)
- [Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling](https://mlsanity.com/paper/2302.01312/) (2023)

## Built on by (most cited first, 22 of 22)

- [Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation](https://mlsanity.com/paper/2412.06781/) (2024)
- [Generative Uncertainty in Diffusion Models](https://mlsanity.com/paper/2502.20946/) (2025)
- [World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty](https://mlsanity.com/paper/2512.05927/) (2025)
- [Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation](https://mlsanity.com/paper/2412.03178/) (2024)
- [How Confident are Video Models? Empowering Video Models to Express their Uncertainty](https://mlsanity.com/paper/2510.02571/) (2025)
- [DiffusionRollout: Uncertainty-Aware Rollout Planning in Long-Horizon PDE Solving](https://mlsanity.com/paper/2602.13616/) (2026)
- [Trustworthy image-to-image translation: evaluating uncertainty calibration in unpaired training scenarios](https://mlsanity.com/paper/2501.17570/) (2025)
- [Flow Matching with Uncertainty Quantification and Guidance](https://mlsanity.com/paper/2602.10326/) (2026)
- [Uncertainty Quantification for Flow-Based Vision-Language-Action Models](https://mlsanity.com/paper/2606.18043/) (2026)
- [Improved probabilistic regression using diffusion models](https://mlsanity.com/paper/2510.04583/) (2025)
- [Quantifying Epistemic Uncertainty in Diffusion Models](https://mlsanity.com/paper/2602.09170/) (2026)
- [Perfecting Depth: Uncertainty-Aware Enhancement of Metric Depth](https://mlsanity.com/paper/2506.04612/) (2025)
- [Efficient Credal Prediction through Decalibration](https://mlsanity.com/paper/2603.08495/) (2026)
- [Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging](https://mlsanity.com/paper/2603.21717/) (2026)
- [EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion](https://mlsanity.com/paper/2505.13273/) (2025)
- [Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena](https://mlsanity.com/paper/2604.22990/) (2026)
- [Uncertainty Quantification for Large Language Diffusion Models](https://mlsanity.com/paper/2605.14570/) (2026)
- [Uncertainty Estimation for Molecular Diffusion Models](https://mlsanity.com/paper/2606.13451/) (2026)
- [LM-X: Explainable Vision--Language--Action Modeling via Progress, Event, and Uncertainty Prediction](https://mlsanity.com/paper/2608.25757/) (2026)
- [Is your uncertainty map wrong, or is its target? Exact diagnostics for the Tweedie diagonal, and a gradient-free alternative](https://mlsanity.com/paper/2609.33786/) (2026)
- [Generative Uncertainty as a Self-supervised Signal for Semantic Similarity Learning](https://mlsanity.com/paper/2609.35341/) (2026)
- [Matisse: Evidence-Space Reasoning for Active 3D Reconstruction](https://mlsanity.com/paper/2609.38746/) (2026)

## Abstract (arXiv)

Generative diffusion models, notable for their large parameter count (exceeding 100 million) and operation within high-dimensional image spaces, pose significant challenges for traditional uncertainty estimation methods due to computational demands. In this work, we introduce an innovative framework, Diffusion Ensembles for Capturing Uncertainty (DECU), designed for estimating epistemic uncertainty for diffusion models. The DECU framework introduces a novel method that efficiently trains ensembles of conditional diffusion models by incorporating a static set of pre-trained parameters, drastically reducing the computational burden and the number of parameters that require training. Additionally, DECU employs Pairwise-Distance Estimators (PaiDEs) to accurately measure epistemic uncertainty by evaluating the mutual information between model outputs and weights in high-dimensional spaces. The effectiveness of this framework is demonstrated through experiments on the ImageNet dataset, highlighting its capability to capture epistemic uncertainty, specifically in under-sampled image classes.