AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Data-Free Quantization Through Weight Equalization and Bias Correction

Markus Nagel, Mart van Baalen, Tijmen Blankevoort, Max Welling

ICCV 2019 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 552 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 cross-layer equalization (ablation)MobileNetV2 INT8 per-tensor · ImageNet valtop-1 accuracy (%): 0.11% -> 69.91%Improved
add high-bias absorption on top of equalization (ablation)MobileNetV2 INT8 per-tensor · ImageNet valtop-1 accuracy (%): 69.91% -> 70.92%Improved
add bias correction alone (ablation)MobileNetV2 INT8 per-tensor · ImageNet valtop-1 accuracy (%): 0.12% -> 52.02%Improved
add bias correction to weight clipping at 15 (ablation)MobileNetV2 INT8 per-tensor · ImageNet valtop-1 accuracy (%): 2.55% -> 70.43%Improved
add bias correction to weight clipping at 15 (full precision) (ablation)MobileNetV2 FP32 · ImageNet valtop-1 accuracy (%): 67.06% -> 71.15%Improved
add bias correction to equalization plus bias absorption (ablation)MobileNetV2 INT8 per-tensor · ImageNet valtop-1 accuracy (%): 70.92% -> 71.19%Improved
replace ReLU6 with ReLU (ablation)MobileNetV2 · ImageNet valtop-1 accuracy FP32 (%): 71.72% -> 71.70%No clear effect
use empirical instead of analytic bias correction (ablation)DFQ MobileNetV2 · ImageNet valtop-1 accuracy (%): 71.19% -> 71.15%No clear effect
add 1 epoch quantization-aware fine-tuning after DFQMobileNetV2 · ImageNet valtop-1 accuracy (%): 71.19% -> 71.42%Improved
use asymmetric instead of symmetric quantization with DFQ (ablation)DFQ MobileNetV1 · ImageNet valtop-1 accuracy (%): 70.32% -> 70.51%No clear effect
add cross-layer equalization to per-channel quantization (ablation)MobileNetV2 per-channel · ImageNet valtop-1 accuracy (%): 70.65% -> 70.93%Improved
add bias correction to CLE+BA with per-channel quantization (ablation)MobileNetV2 per-channel · ImageNet valtop-1 accuracy (%): 71.03% -> 71.33%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