Jun, 2024

揭示大型生成网络的光芒:扩散模型中估计认识不确定性

TL;DRDiffusion Ensembles for Capturing Uncertainty (DECU) is an innovative framework designed to estimate epistemic uncertainty in generative diffusion models by efficiently training ensembles of conditional diffusion models with a static set of pre-trained parameters and employing Pairwise-Distance Estimators (PaiDEs) to accurately measure epistemic uncertainty in high-dimensional spaces.