AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Entropy-Driven Mixed-Precision Quantization for Deep Network Design

Zhenhong Sun, Ce Ge, Junyan Wang, Ming Lin, Hesen Chen, Hao Li, Xiuyu Sun

NeurIPS 2022 · Architectures and efficiency › Quantization · approach: Mixed-precision quantization · 2 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
Quantization Bits Refinement (QBR) (ablation)Ours-mixed · 256kB SRAM, 1MB FlashTOP-1 accuracy: 65.6% -> 66.5%Improved
Quantization Bits Refinement (QBR) (ablation)Ours-mixed · 320kB SRAM, 1MB FlashTOP-1 accuracy: 66.6% -> 68.2%Improved
Quantization Bits Refinement (QBR) (ablation)Ours-mixed · 512kB SRAM, 2MB FlashTOP-1 accuracy: 71.7% -> 72.8%Improved
Mixed precision instead of fixed 4-bit (ablation)Ours · 256kB SRAM, 1MB FlashTOP-1 accuracy: 64.4% -> 66.5%Improved
Mixed precision instead of fixed 8-bit (ablation)Ours · 256kB SRAM, 1MB FlashTOP-1 accuracy: 62.7% -> 66.5%Improved
Fixed 4-bit instead of fixed 8-bit (ablation)Ours · 512kB SRAM, 2MB FlashTOP-1 accuracy: 70.4% -> 71.0%Improved
Ours-19.2G search vs MobileNetV2 8-bitMobileNetV2 · ImageNet, 19.2G BitOpsTOP-1 accuracy: 71.9% -> 74.8%Improved
Ours-7.0G search vs MobileNetV2 4-bitMobileNetV2 · ImageNet, 7.0G BitOpsTOP-1 accuracy: 68.9% -> 70.8%Improved
Ours vs MCUNet-int8MCUNet · 256kB SRAM, 1MB FlashTOP-1 accuracy: 60.3% -> 66.5%Improved
Ours vs MCUNet-int4MCUNet · 256kB SRAM, 1MB FlashTOP-1 accuracy: 62.0% -> 66.5%Improved
Ours vs MCUNetV2MCUNetV2 · 512kB SRAM, 2MB FlashTOP-1 accuracy: 71.8% -> 72.8%Improved
Ours-Face vs MCUNetV2 on WIDER FACEMCUNetV2 · WIDER FACE HardmAP: 0.55 -> 0.77Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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