AI Paper Atlas

Research map / Architectures and efficiency / Quantization

TexQ: Zero-shot Network Quantization with Texture Feature Distribution Calibration

Xinrui Chen, Yizhi Wang, Renao Yan, Yiqing Liu, Tian Guan, Yonghong He

NeurIPS 2023 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 4 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
remove both L_LAWS and L_L-BNS (only MKD kept) (ablation)TexQ · ImageNet W3A3 ResNet-18top-1 accuracy (%): 50.94 -> 42.57Hurt
add calibration losses L_LAWS and L_L-BNS together (ablation)TexQ · ImageNet W3A3 ResNet-18top-1 accuracy (%): 8.37% loss when removedImproved
drop one or two of the three modules (ablation)TexQ · ImageNet W3A3 ResNet-18top-1 accuracy (%): 50.94 -> 49.03Hurt
replace prior best AdaDFQ with TexQ at 3-bitResNet-18 · ImageNet W3A3top-1 accuracy (%): 38.10 -> 50.28Improved
replace AdaDFQ with TexQ at 4-bitResNet-18 · ImageNet W4A4top-1 accuracy (%): 66.53 -> 67.73Improved
replace AdaDFQ with TexQ at 3-bitResNet-50 · ImageNet W3A3top-1 accuracy (%): 17.63 -> 25.27Improved
replace AdaDFQ with TexQ at 3-bitResNet-20 · CIFAR-10 W3A3top-1 accuracy (%): 84.89 -> 86.47Improved
replace AdaDFQ with TexQ at 3-bitResNet-20 · CIFAR-100 W3A3top-1 accuracy (%): 52.74 -> 55.87Improved
replace AdaDFQ with TexQ at 4-bitResNet-20 · CIFAR-10 W4A4top-1 accuracy (%): 92.31 -> 92.68Improved
TexQ vs real-data fine-tuning with same frameworkResNet-20 · CIFAR-10 W4A4top-1 accuracy (%): 91.52 -> 92.68Improved
grid-search texture hyperparameters k, theta_U, theta_L, epsilon (ablation)TexQ · ImageNet W3A3 ResNet-18top-1 accuracy (%): best 50.94Mixed
mixup probability p=20% for MKD (ablation)TexQ · ImageNet W3A3top-1 accuracy (%)Improved

Later papers that compared with this method

3 later accepted papers report TexQ as a baseline in their results tables; 3 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