AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree

Quang Hieu Vo, Linh-Tam Tran, Sung-Ho Bae, Lok-Won Kim, Choong Seon Hong

ICCV 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 4 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
replace K-mean reordering with MST reordering in the hardware design (ablation)BNN FPGA accelerator · CIFAR-10 FPGAFPS/LUTs: 1.01 -> 1.27Improved
use MST instead of shortest Hamiltonian path to reorder computation (ablation)ResNet-20 binary conv layers · ResNet-20 layer 1exploration time: 31.3 s -> 0.021 sImproved
use MST instead of K-mean for reordering (ablation)ResNet-20 binary conv layers · ResNet-20 layer 1Bit-Ops: 1.33 M -> 1.07 MImproved
apply MST reordering directly to pretrained BNN (no retraining)ReCU VGG-small · CIFAR-10Top-1 accuracy: 92.4 -> 93.3No clear effect
add MST distance loss during training (Ours 1) on ImageNet ResNet-18ReCU ResNet-18 · ImageNetTop-1 accuracy: 61.0 -> 57.0Hurt
increase MST loss weight lambda from 1e-7 to 1e-5 (ablation)VGG-small · CIFAR-10Top-1 accuracy: 92.17 -> 90.17Hurt
increase lambda from 1e-7 to 1e-5 (ablation)VGG-small · CIFAR-10Params (Mbit): 1.391 -> 0.422Improved
use a single initial center instead of 8 (ablation)MST learning · CIFAR-10 VGG-smallMST depth: 73.0 -> 22.3Improved
vary number of centers from 1 to 8 (ablation)MST learning · CIFAR-10 VGG-smallTop-1 accuracy: 91.49 -> 91.49No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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