AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Capsule Network Is Not More Robust Than Convolutional Network

Jindong Gu, Volker Tresp, Han Hu

CVPR 2021 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 41 citations (OpenAlex)

Check 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 global average pooling to the ConvNet classifierConvNet-Avg · AffNISTaccuracy: 66 -> 94.11Improved
remove dynamic routing (ablation)CapsNet · AffNISTaccuracy: 90.07{ ($\pm$ 0.98)} -> 93.55{ ($\pm$ 1.47)}Improved
share the transformation matrix (ablation)CapsNet without routing · AffNISTaccuracy: 80.49{ ($\pm$ 0.34)} -> 93.55{ ($\pm$ 1.47)}Improved
add the squashing function (ablation)CapsNet without routing · AffNISTaccuracy: 80.42{ ($\pm$ 0.39)} -> 93.55{ ($\pm$ 1.47)}Improved
use normal rather than conditional reconstruction (ablation)CapsNet without routing · AffNISTaccuracy: 93.55{ ($\pm$ 1.47)} -> 95.09{ ($\pm$ 0.56)}Improved
replace margin loss with cross-entropy loss (ablation)CapsNet without routing · AffNISTaccuracy: 93.55{ ($\pm$ 1.47)} -> 94.67{ ($\pm$ 0.43)}Improved
use large kernels in ConvNet-FCConvNet-FC(LK) · MultiMNISTaccuracy: 95.18\% -> 97.11\%Improved
remove dynamic routing (ablation)CapsNet · MultiMNISTaccuracy: 93.26{ ($\pm$ 0.24)} -> 90.07{ ($\pm$ 0.29)}Hurt
use a shared transformation matrix (ablation)CapsNet · MultiMNISTaccuracy: 93.26{ ($\pm$ 0.24)} -> 86.44{ ($\pm$ 0.37)}Hurt
remove the squashing function (ablation)CapsNet · MultiMNISTaccuracy: 93.26{ ($\pm$ 0.24)} -> 87.24{ ($\pm$ 0.53)}Hurt
replace conditional reconstruction with normal reconstruction (ablation)CapsNet · MultiMNISTaccuracy: 93.26{ ($\pm$ 0.24)} -> 93.19{ ($\pm$ 0.30)}No clear effect
remove reconstruction (ablation)CapsNet · MultiMNISTaccuracy: 93.26{ ($\pm$ 0.24)} -> 90.17{ ($\pm$ 0.26)}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