AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Weighted Channel Dropout for Regularization of Deep Convolutional Neural Network

Saihui Hou, Zilei Wang

AAAI 2019 · Architectures and efficiency › CNN design · approach: Theory of convolutional inductive bias · 85 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 WCD to VGGNet-16VGGNet-16 · CUB-200-2011top-1 accuracy: 72.31% -> 76.10%Improved
add WCD to ResNet-101ResNet-101 · CUB-200-2011top-1 accuracy: 76.45% -> 77.22%Improved
add WCD to Inception-V3Inception-V3 · Stanford Carstop-1 accuracy: 93.17% -> 93.41%Improved
add WCD to Inception-V3Inception-V3 · Caltech-256top-1 accuracy: 79.52% -> 80.61%Improved
add WCD to Compact Bilinear CNNCompact Bilinear CNN · CUB-200-2011top-1 accuracy: 84.01% -> 84.88%Improved
add WCD (wrs 0.9, q 0.5) rather than Dropout after pool5 (ablation)VGGNet-16 · CUB-200-2011top-1 accuracy: 73.90% -> 75.60%Improved
add WCD rather than SE-Block after pool5 (ablation)VGGNet-16 · CUB-200-2011top-1 accuracy: 73.05% -> 75.60%Improved
use weighted random selection with RNG (q<1) instead of q=1 (ablation)WCD on VGGNet-16 · CUB-200-2011top-1 accuracy: 73.28% -> 75.60%Improved
use weighted selection (wrs<1) instead of Channel-wise Dropout (wrs=1) (ablation)WCD on VGGNet-16 · CUB-200-2011top-1 accuracy: 75.02% -> 75.60%Improved
SE-Block pretrained on ImageNet vs not (ablation)VGGNet-16 · CUB-200-2011top-1 accuracy: 72.71% -> 73.05%Improved
very low keep ratio (wrs 1 q 0.25 or wrs 0.25 q 1) (ablation)WCD on VGGNet-16 · CUB-200-2011top-1 accuracy: 75.60% -> 73.16%; 72.16%Hurt

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