AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Yuexiao Ma, Huixia Li, Xiawu Zheng, Xuefeng Xiao, Rui Wang, Shilei Wen, Xin Pan, Fei Chao, Rongrong Ji

CVPR 2023 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 16 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 MRECG to BRECQBRECQ · ImageNet val, ResNet-18 W/A 2/4Top-1 accuracy (%): 63.71 -> 65.61 (+1.9)Improved
Add MRECG to BRECQBRECQ · ImageNet val, MobileNetV2 ×0.5 W/A 2/4Top-1 accuracy (%): 34.55 -> 41.16 (+6.61)Improved
Add MRECG to QDROPQDROP · ImageNet val, Reg600M W/A 2/4Top-1 accuracy (%): 63.10 -> 65.16 (+2.06)Improved
Add mixed reconstruction granularity (ablation)BRECQ on MobileNetV2 ×0.5 W/A 4/4 · ImageNet valTop-1 accuracy (%): 50.83 -> 51.91Improved
Expand calibration batch size (ablation)BRECQ on MobileNetV2 ×0.5 W/A 4/4 · ImageNet valTop-1 accuracy (%): 50.83 -> 51.57Improved
Combine MRECG with expanded calibration batch size (ablation)BRECQ on MobileNetV2 ×0.5 W/A 4/4 · ImageNet valTop-1 accuracy (%): 50.83 -> 52.25Improved
Use reconstruction loss rather than ModCap to choose module combinations (ablation)MRECG · ImageNet val, ResNet-18 W/A 3/3Top-1 accuracy (%): 66.07 -> 66.30Improved
Use reconstruction loss rather than ModCap to choose module combinations (ablation)MRECG · ImageNet val, MobileNetV2 ×0.5 W/A 3/3Top-1 accuracy (%): 38.02 -> 38.43Improved
Increase calibration batch size (ablation)PTQ reconstruction · ImageNet val, MobileNetV2 ×0.5 W/A 4/4Top-1 accuracy (%)Mixed
Jointly optimize adjacent modules with large capacity differences (ablation)PTQ reconstruction · ImageNet classificationReconstruction loss oscillationImproved

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