AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Extreme Network Compression via Filter Group Approximation

Bo Peng, Wenming Tan, Zheyang Li, Shun Zhang, Di Xie, Shiliang Pu

ECCV 2018 · Architectures and efficiency › CNN design · approach: CNN filter pruning · 68 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
compress with filter group approximation instead of asymmetric low-rank decompositionVGG16(S) · CIFAR100 (88% FLOPs reduction)top-1 accuracy loss: 4.47% -> 1.93%Improved
compress with filter group approximation instead of asymmetric low-rank decompositionVGG16 · ImageNet (about 7x speed-up)top-5 accuracy loss: 5.14% -> 2.03%Improved
compress with filter group approximation instead of asymmetric low-rank decompositionResNet34 · ImageNet (84.8% FLOPs reduction)top-5 accuracy loss: 8.27% -> 1.22%Improved
compress with filter group approximation instead of Li et al. filter pruningResNet34 · ImageNet (84.84% FLOPs reduction)top-1 accuracy loss: 13.27% -> 3.03%Improved
add spatial decomposition (3D) to the Asym. baselineAsym. · ImageNet ResNet34top-5 accuracy loss: 8.27% -> 2.78%Improved
use Quarter compression schedule (n ratio 1:4 between stages) instead of Constant or Half (ablation)ResNet34 compression · ImageNettop-5 accuracyImproved
compress the network with filter group approximation instead of training same architecture from scratch (ablation)VGG16 compressed 57% · ImageNetaccuracyImproved
initialize with filter group approximation instead of MSRA or orthogonal initialization (ablation)Ours-Res34/A · ImageNetaccuracy lossImproved
use filter group approximation instead of asymmetric decomposition for CPU latencyVGG16 (85.80% FLOPs reduction) · ImageNet CPU timems per image: 2078 -> 628Improved
run filter group convolution on Caffe GPUVGG16 compressed · TITAN-XP GPU timems per image: 2.91 -> 2.17Hurt

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