AI Paper Atlas

Research map / Architectures and efficiency / Quantization

LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks

Dongqing Zhang, Jiaolong Yang, Dongqiangzi Ye, Gang Hua

ECCV 2018 · Architectures and efficiency › Quantization · approach: Mixed-precision quantization · 740 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
optimize quantizers with QEM instead of backprop (ablation)LQ-Nets ResNet-20 · CIFAR-10 (2/32)accuracy: 90.0 -> 91.8Improved
optimize quantizers with QEM instead of backprop (ablation)LQ-Nets ResNet-20 · CIFAR-10 (2/2)accuracy: 88.2 -> 90.2Improved
increase QEM iterations T from 1 to 4 (ablation)LQ-Nets ResNet-20 · CIFAR-10 (2/2)accuracy: 90.16 -> 90.25No clear effect
increase QEM iterations T from 1 to 4 (ablation)LQ-Nets ResNet-20 · CIFAR-10 (1/2)accuracy: 88.37 -> 88.51No clear effect
increase QEM iterations T from 1 to 4 (ablation)LQ-Nets ResNet-20 · CIFAR-10 (3/3)accuracy: 91.58 -> 91.44No clear effect
learn the quantizer instead of fixed half-wave Gaussian quantizerResNet-18 1/2 · ImageNettop-1 accuracy: 59.6 -> 62.6Improved
learn the quantizer instead of fixed uniform quantizerResNet-18 1/2 vs DoReFa 1/4 · ImageNettop-1 accuracy: 59.2 -> 62.6Improved
learned quantizer instead of HWGQVGG-Small 1/2 · CIFAR-10accuracy: 92.5 -> 93.4Improved
increase bits from 1/2 to 4/4 (ablation)LQ-Nets ResNet-50 · ImageNettop-1 accuracy: 68.7 -> 75.1Improved
increase activation bits 2 to 3 to 4 with 2/32 to 4/32 weights (ablation)LQ-Nets ResNet-18 · ImageNettop-1 accuracy: 68.0 -> 70.0Improved
quantize to 1/2 bits instead of full precision (ablation)LQ-Nets ResNet-18 · ImageNettop-1 accuracy: 70.3 -> 62.6Hurt
increase weight bits from 1 to 3 on CIFAR-10 (ablation)LQ-Nets VGG-Small · CIFAR-10accuracy: 93.5 -> 93.8Improved

Later papers that compared with this method

1 later accepted paper reports LQNets 4/32 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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