AI Paper Atlas

Research map / Architectures and efficiency / Quantization

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

Cong Guo, Yuxian Qiu, Jingwen Leng, Xiaotian Gao, Chen Zhang, Yunxin Liu, Fan Yang, Yuhao Zhu, Minyi Guo

ICLR 2022 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 19 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
Use SQuant instead of the strongest listed baselineResNet18, 4-bit weight and activation quantization · ImageNetTop-1: 60.60 -> 66.14Improved
Use SQuant instead of the strongest listed baselineResNet50, 4-bit weight and activation quantization · ImageNetTop-1: 55.65 -> 70.80Improved
Use SQuant instead of the strongest listed baselineInceptionV3, 8-bit weight and activation quantization · ImageNetTop-1: 78.78 -> 78.79No clear effect
Use SQuant instead of the strongest listed baselineSqueezeNext, 4-bit weight and activation quantization · ImageNetTop-1: 28.93 -> 43.45Improved
Use SQuant instead of the strongest listed baselineShuffleNet, 8-bit weight and activation quantization · ImageNetTop-1: 64.34 -> 64.68Improved
Add output-channel and kernel-wise optimization to element-wise rounding (ablation)SQuant on ResNet18 · ImageNet (weight-only, 3-bit)Top-1: 2.05 -> 60.78Improved
Add output-channel and kernel-wise optimization to element-wise rounding (ablation)SQuant on ResNet18 · ImageNet (weight-only, 4-bit)Top-1: 48.15 -> 69.75Improved
Add output-channel optimization to element-wise rounding (ablation)SQuant on ResNet18 · ImageNet (weight-only, 4-bit)Top-1: 48.15 -> 67.14Improved
Add kernel-wise optimization to element-wise rounding (ablation)SQuant on ResNet18 · ImageNet (weight-only, 4-bit)Top-1: 48.15 -> 68.07Improved
Add output-channel optimization to element-wise and kernel-wise optimization (ablation)SQuant on ResNet18 · ImageNet (weight-only, 4-bit)Top-1: 68.07 -> 69.75Improved

Later papers that compared with this method

4 later accepted papers report SQuant as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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