AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning

Shipeng Bai, Jun Chen, Xintian Shen, Yixuan Qian, Yong Liu

ICCV 2023 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 26 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
add linear-combination channel reconstruction after pruning (UDFC vs plain pruning)structured pruning · ImageNet pruning 30%Top-1 accuracy (%): 10.10 -> 65.76 (ResNet-101, l2-norm, with 6-bit)Improved
replace one-to-one Neuron Merging compensation with many-to-one linear combination reconstructiondata-free pruning · CIFAR-10 VGG-16 80% pruningaccuracy (%): 40.26 -> 91.79Improved
data-free UDFC weight quantization instead of data-driven PTQ (DSG, SQuant)ResNet-18 W6/A6 · ImageNetTop-1 accuracy (%): 70.74 -> 72.76 (vs SQuant)Improved
increase pruning ratio (ablation)UDFC · ResNet-56 CIFAR-10accuracy: 30%: 90.33; 40%: 86.99; 50%: 81.90Hurt
reduce weight bit-width to 4-bit (ablation)UDFC · ResNet-56 CIFAR-10accuracyMixed
add bias-term weighting alpha1 in reconstruction error (0 -> 0.01, then 0.04) (ablation)UDFC pruning (50% ResNet-56) · CIFAR-10accuracyMixed
tune alpha2 for 2-bit quantization (ablation)UDFC quantization (ResNet-56) · CIFAR-10accuracyMixed
use UDFC at very low bit-widths (3-bit, 2-bit)UDFC · ResNet-56 CIFAR-10accuracyHurt
replace data-free-synthetic-sample quantization with data-free closed-form quantizationResNet-50 quantization · ImageNetquantization time: 29 seconds (ZeroQ, 8 V100) -> 2 seconds (UDFC, 1 RTX 1080Ti)Improved

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