AI Paper Atlas

Research map / Architectures and efficiency / CNN design

HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks

Miao Yin, Yang Sui, Wanzhao Yang, Xiao Zang, Yu Gong, Bo Yuan

CVPR 2022 · Architectures and efficiency › CNN design · approach: CNN filter pruning · 17 citations (OpenAlex)

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 HODEC compression instead of the uncompressed modelResNet-32 · CIFAR-10top-1 accuracy: 92.49 -> 93.05Improved
Use HODEC compression instead of the uncompressed modelResNet-56 · CIFAR-10top-1 accuracy: 93.04 -> 94.20Improved
Use HODEC compression instead of the uncompressed modelResNet-50 · ImageNettop-1 accuracy: 76.13 -> 76.44Improved
Use HODEC compression instead of the uncompressed modelResNet-50 · ImageNetFLOPs: 63%Improved
Add core convolution between contract-in and contract-out (ablation)HODEC · CIFAR-10, ResNet-32 trained from scratchtop-1 accuracy: nearly 2%Improved
Use one-stage end-to-end decomposition instead of two-stage decomposition (ablation)HODEC weight decomposition · ResNet-32 convolution layerapproximation errorImproved
Increase decomposition order d (ablation)HODEC, ResNet-18 layer3.0.conv1 · ImageNetFLOPs reductionHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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