AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture Search

Mingzhu Shen, Feng Liang, Ruihao Gong, Yuhang Li, Chuming Li, Chen Lin, Fengwei Yu, Junjie Yan, Wanli Ouyang

ICCV 2021 · Architectures and efficiency › Quantization · approach: Mixed-precision quantization · 48 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
search architecture on the 2-bit supernet instead of FP supernet (joint training) (ablation)OQAT 2-bit · ImageNet 2-bittop-1 accuracy (%): 54.4% -> 56.1%Improved
search architecture on the 2-bit supernet with QAT@150 finetuning (ablation)OQAT 2-bit · ImageNet 2-bittop-1 accuracy (%): 28.1% -> 33.2%Improved
search architecture on the 2-bit supernet with QAT@500 finetuning (ablation)OQAT 2-bit · ImageNet 2-bittop-1 accuracy (%): 43.5% -> 47.2%Improved
initialize 2-bit supernet with bit inheritance instead of plain QAT (ablation)OQAT 2/2 · ImageNet 2-bittop-1 accuracy (%): 56% -> 64.5%Improved
initialize 3-bit supernet with bit inheritance instead of plain QAT (ablation)OQAT 3/3 · ImageNet 3-bittop-1 accuracy (%): 72.1% -> 72.7%Improved
bit inheritance start accuracy vs QAT start accuracy at 2-bit (ablation)OQAT 2/2 · ImageNet 2-bittop-1 accuracy at first epoch (%): 0.8% -> 49.3%Improved
use supernet trained at 4-bit with shared step size (OQAT-4bit) instead of individual 4-bit QAT, calibrated to 3/3 (ablation)biggest model · ImageNet 3/3top-1 accuracy (%): 65.3% -> 69.1%Improved
calibrate OQAT-4bit supernet to 3/4 bits (ablation)biggest model · ImageNet 3/4top-1 accuracy (%): 69.2% -> 72.1%Improved
fine-tune the inherited 3-bit supernet for one epoch (ablation)bit inheritance 3-bit · ImageNet 3-bittop-1 accuracy: 2.6%Improved
choose wider models at fixed floating-point accuracyarchitecture analysis · sampled subnets 2-bitquantization friendlinessImproved
increase input resolution at similar FLOPsarchitecture analysis · sampled subnets 2-bitquantization friendlinessImproved
increase network depth at fixed FLOPsarchitecture analysis · sampled subnets 2-bitquantization friendlinessHurt

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