AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations

Zhaoyi Yan, Yemin Shi, Yaowei Wang, Mingkui Tan, Zheyang Li, Wenming Tan, Yonghong Tian

AAAI 2020 · Architectures and efficiency › Quantization · approach: Mixed-precision quantization · 3 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 MPA (multiple phase adaptations) to 3-bit quantization (ablation)ResNet-18 · ImageNet valtop-1 accuracy (%): 66.9 -> 69.7Improved
add MPA to 4-bit quantization (ablation)ResNet-18 · ImageNet valtop-1 accuracy (%): 68.6 -> 70.2Improved
add MPA to 3-bit quantization (ablation)ResNet-18 · CIFAR-10top-1 accuracy (%): 91.6 -> 93.1Improved
add MPA to 4-bit quantization (ablation)ResNet-18 · CIFAR-10top-1 accuracy (%): 92.3 -> 93.4Improved
longer training (64 epochs vs 32 epochs)MPA ResNet-18 3-bit · ImageNet valtop-1 accuracy (%): 68.9 -> 69.7Improved
longer training (64 epochs vs 32 epochs)MPA AlexNet 4-bit · ImageNet valtop-1 accuracy (%): 55.8 -> 56.2Improved
longer training (64 epochs vs 32 epochs)MPA VGG-16 3-bit · ImageNet valtop-1 accuracy (%): 70.8 -> 71.4Improved
longer training (64 epochs vs 32 epochs)MPA ResNet-50 3-bit · ImageNet valtop-1 accuracy (%): 74.8 -> 75.1Improved
longer training (64 epochs vs 32 epochs)MPA ResNet-18 ternary · ImageNet valtop-1 accuracy (%): 67.2 -> 69.2Improved
linear division of weight centers instead of clustering (ablation)MPA ResNet-18 3-bit · ImageNet valtop-1 accuracy (%): 69.7 -> 67.6Hurt
linear division of weight centers instead of clustering (ablation)MPA ResNet-18 4-bit · ImageNet valtop-1 accuracy (%): 70.2 -> 68.9Hurt
exponential division of weight centers instead of clustering (ablation)MPA ResNet-18 3-bit · ImageNet valtop-1 accuracy (%): 69.7 -> 69.5No clear effect

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