paper-with-me

홈 › Papers

FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty

2026-06-01 · Harry Zhang, Luca Carlone arxiv

Vision-language models (VLMs) are playing an increasingly important role across multiple domains. In many applications, such as robotics, it is crucial to quantify the uncertainty in the output of these models. } We develop FUSE, a probabilistic framework for capturing two complementary sources of uncertainty in vision-language modeling: (i) aleatoric embedding-level uncertainty derived from input data vision-language ambiguity, and (ii) epistemic model-level uncertainty estimated from the semantic response diversity of VLMs. Our approach formulates a Bayesian fusion mechanism that analytically combines these uncertainty sources to produce a scalar measure of uncertainty. This measure can be used to reliably predict the model's output correctness for downstream applications. We demonstrate that our method outperforms baselines and achieves SOTA uncertainty calibration.

📄 PDF Abstract BibTeX arXiv:2606.14728

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Quantifying uncertainty with GAN-based priors

2019-09-25 · Dhruv V. Patel, Assad A. Oberai

Bayesian inference is used extensively to quantify the uncertainty in an inferred field given the measurement of a related field when the two are linked by a mathematical model. Despite its many applications, Bayesian in…

Bayesian InferenceGenerative Adversarial Network

Multi-Fidelity Bayesian Neural Network for Uncertainty Quantification in Transonic Aerodynamic Loads

2024-07-08 · Andrea Vaiuso, Gabriele Immordino, Marcello Righi, Andrea Da Ronch

Multi-fidelity models are becoming more prevalent in engineering, particularly in aerospace, as they combine both the computational efficiency of low-fidelity models with the high accuracy of higher-fidelity simulations.…

Computational EfficiencyTransfer LearningUncertainty Quantification

On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees

2024-10-20 · Yijie Zhang

Bayesian inference provides a principled probabilistic framework for quantifying uncertainty by updating beliefs based on prior knowledge and observed data through Bayes' theorem. In Bayesian deep learning, neural networ…

Bayesian InferenceGeneralization Bounds

GAN priors for Bayesian inference

2019-09-14 · NeurIPS Workshop Deep_Invers 2019 12 · Dhruv V. Patel, Assad A. Oberai

Bayesian inference is used extensively to infer and to quantify the uncertainty in a field of interest from a measurement of a related field when the two are linked by a mathematical model. Despite its many applications,…

Bayesian InferenceGenerative Adversarial Network

A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications

2021-11-03 · Xinlei Zhou, Han Liu, Farhad Pourpanah, Tieyong Zeng 외

Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient knowledge about the model, can be reduced…