AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Curriculum Dropout

Pietro Morerio, Jacopo Cavazza, Riccardo Volpi, Rene Vidal, Vittorio Murino

ICCV 2017 · Architectures and efficiency › RNNs and normalization · approach: Weight normalization and decay interplay · 107 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
use Curriculum Dropout instead of standard DropoutDropout · Double MNIST (CNN-2, n fixed)accuracy gain over unregularized: +1.42 -> +2.35Improved
use Curriculum Dropout instead of standard DropoutDropout · CIFAR-10 (CNN-1)accuracy gain over unregularized: +0.22 -> +0.62Improved
use Curriculum Dropout instead of standard DropoutDropout · CIFAR-100 (CNN-1)accuracy gain over unregularized: +1.01 -> +1.66Improved
use Curriculum Dropout instead of standard DropoutDropout · Caltech-256 (CNN-2)accuracy gain over unregularized: +2.36 -> +3.23Improved
use Curriculum Dropout instead of standard DropoutDropout · Caltech-101 (CNN-2)accuracy gain over unregularized: +4.21 -> +4.72Improved
use Curriculum Dropout instead of standard DropoutDropout · SVHN (CNN-2, n fixed)accuracy gain over unregularized: +2.35 -> +2.65Improved
use Curriculum Dropout instead of standard DropoutDropout · MNIST (MLP)accuracy gain over unregularized: +0.38 -> +0.36No clear effect
use Curriculum Dropout instead of standard DropoutDropout · MNIST (CNN-1)accuracy gain over unregularized: +0.15 -> +0.18Improved
use decreasing retain probability (curriculum) instead of linearly increasing (anti-curriculum) (ablation)Anti-Curriculum Dropout · CIFAR-10 (CNN-1)accuracy gain over unregularized: -0.68 -> +0.62Improved
use decreasing retain probability (curriculum) instead of linearly increasing (anti-curriculum) (ablation)Anti-Curriculum Dropout · Caltech-256 (CNN-2)accuracy gain over unregularized: -0.22 -> +3.23Improved
use Curriculum Dropout instead of anti-curriculum (ablation)Anti-Curriculum Dropout · Double MNIST (CNN-2, n fixed)accuracy gain over unregularized: +0.73 -> +2.35Improved
use smooth exponential schedule instead of a Switch-Curriculum step function (ablation)Curriculum Dropout · Double MNISTtest accuracyImproved

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