# Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation

arXiv: https://arxiv.org/abs/2511.12389 · HTML: https://mlsanity.com/paper/2511.12389/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 43 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion](https://mlsanity.com/paper/2111.14690/) (2021)
- [MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors](https://mlsanity.com/paper/2211.09791/) (2022)

## Built on by (most cited first, 6 of 6)

- [TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning](https://mlsanity.com/paper/2602.11409/) (2026)
- [VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation](https://mlsanity.com/paper/2604.25235/) (2026)
- [Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking](https://mlsanity.com/paper/2602.16160/) (2026)
- [TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same](https://mlsanity.com/paper/2603.08128/) (2026)
- [Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets](https://mlsanity.com/paper/2606.25760/) (2026)
- [CURA: Certified Runtime Alarms for Computer-Use Agents](https://mlsanity.com/paper/2608.27808/) (2026)

## Abstract (arXiv)

Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference. We introduce Uncertainty-Guided Inference-Time Selection, a lightweight inference time framework that disentangles aleatoric (data-driven) and epistemic (model-driven) uncertainty directly in deep feature space. Aleatoric uncertainty is estimated using a regularized global density model, while epistemic uncertainty is formed from three complementary components that capture local support deficiency, manifold spectral collapse, and cross-layer feature inconsistency. These components are empirically orthogonal and require no sampling, no ensembling, and no additional forward passes. We integrate the decomposed uncertainty into a distribution free conformal calibration procedure that yields significantly tighter prediction intervals at matched coverage. Using these components for uncertainty guided adaptive model selection reduces compute by approximately 60 percent on MOT17 with negligible accuracy loss, enabling practical self regulating visual inference. Additionally, our ablation results show that the proposed orthogonal uncertainty decomposition consistently yields higher computational savings across all MOT17 sequences, improving margins by 13.6 percentage points over the total-uncertainty baseline.