AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization

Jiyang Xie, Zhanyu Ma, Jianjun Lei, Guoqiang Zhang, Jing‐Hao Xue, Zheng‐Hua Tan, Jun Guo

TPAMI 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Variational Bayesian deep learning · 71 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SGVB optimization of mask distribution parameters (vs fixed at 0.5) (ablation)advanced dropout · CIFAR-10 (VGG16)accuracy (%): 93.98 -> 94.28Improved
add parametric prior (ablation)advanced dropout · CIFAR-10 (VGG16)accuracy (%): 94.20 -> 94.28Improved
add SGVB optimization of mask distribution parameters (ablation)advanced dropout · CIFAR-100 (VGG16)accuracy (%): 74.55 -> 74.94Improved
add parametric prior (ablation)advanced dropout · CIFAR-100 (VGG16)accuracy (%): 74.77 -> 74.94Improved
add SGVB optimization of mask distribution parameters (ablation)advanced dropout · MNISTaccuracy (%): 98.70 -> 98.89Improved
add parametric prior (ablation)advanced dropout · MNISTaccuracy (%): 98.81 -> 98.89Improved
add parametric prior (ablation)advanced dropout · miniImageNet (VGG16)accuracy (%): 77.30 -> 77.35Improved
add parametric prior (ablation)advanced dropout · Caltech-256 (VGG16)accuracy (%): 65.03 -> 65.09Improved
apply advanced dropout to base modelVGG16 · ImageNet (top-1)accuracy (%): 73.42 -> 74.82Improved
apply advanced dropout to base modelVGG16 · CIFAR-100accuracy (%): 73.62 -> 74.94Improved
apply advanced dropout to base modelWRN16-10 · CIFAR-10accuracy (%): 94.29 -> 95.50Improved
apply advanced dropout to base modelDenseNet40 · CIFAR-100accuracy (%): 68.36 -> 70.65Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy