AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?

Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou, Ozlem Aslan, Shengjie Wang, Abdelrahman Mohamed, Matthai Philipose, Matt Richardson, Rich Caruana

ICLR 2017 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 105 citations (OpenAlex)

This paper tried a common change: Add dropout

Add dropout during student mimic training · CIFAR-10 · accuracy Hurt

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
Train a student on ensemble logits rather than hard labels10M-parameter CNNs with 1–4 convolutional layers · CIFAR-10accuracy: 84.6% -> 87.3%; 88.9% -> 90.0%; 91.2% -> 91.9%; 91.75% -> 92.6%Improved
Add convolution instead of using a fully connected MLP31.6M-parameter CIFAR-10 students · CIFAR-10accuracy: 70.2% -> 87.7%Improved
Increase convolutional depth from 1 to 4 layers31.6M-parameter student CNN · CIFAR-10accuracy: 87.7% -> 92.6%Improved
Increase student CNN parameter budget from 1M to 31.6MStudent CNNs · CIFAR-10accuracy: 84.5% -> 87.7%; 87.9% -> 90.3%; 90.7% -> 92.3%; 91.3% -> 92.6%Improved
Increase MLP depth beyond 2–3 hidden layers without adding convolutionStudent MLPs · CIFAR-10accuracy: 74.3% -> 71.5%Hurt
Add dropout during student mimic training (ablation)Student mimic networks · CIFAR-10accuracyHurt
Add weight decay during student mimic training (ablation)Student mimic networks · CIFAR-10accuracyHurt
Use distillation rather than hard labels for shallow CNN students (ablation)Student CNNs with 1–4 convolutional layers · CIFAR-10accuracy: 2.7%; 0.8%Improved

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