AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Explicit Model Size Control and Relaxation via Smooth Regularization for Mixed-Precision Quantization

Vladimir Chikin, Kirill Solodskikh, Irina Zhelavskaya

ECCV 2022 · Architectures and efficiency › Quantization · approach: Mixed-precision quantization · 5 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 smooth bounded regularizers to bit-width tuning (2-bit) (ablation)bit-width tuning · CIFAR-10 ResNet-20 2-bitTop-1 accuracy (%): 65.94 -> 77.05Improved
add smooth regularizers to bit-widths and scales tuning (2-bit) (ablation)bit-widths and scales tuning · CIFAR-10 ResNet-20 2-bitTop-1 accuracy (%): 79.20 -> 86.85Improved
add smooth regularizers to all-parameter tuning (2-bit) (ablation)full QAT · CIFAR-10 ResNet-20 2-bitTop-1 accuracy (%): 91.27 -> 91.57Improved
add smooth regularizers to bit-width tuning (3-bit) (ablation)bit-width tuning · CIFAR-10 ResNet-20 3-bitTop-1 accuracy (%): 89.70 -> 90.13Improved
add smooth regularizers to all-parameter tuning (3-bit) (ablation)full QAT · CIFAR-10 ResNet-20 3-bitTop-1 accuracy (%): 91.69 -> 91.89Improved
also tune scales, not only bit-widths (2-bit, no regularizers) (ablation)bit-width tuning · CIFAR-10 ResNet-20 2-bitTop-1 accuracy (%): 65.94 -> 79.20Improved
also tune all model weights (2-bit, no regularizers) (ablation)bit-widths and scales tuning · CIFAR-10 ResNet-20 2-bitTop-1 accuracy (%): 79.20 -> 91.27Improved
bit-width tuning instead of BN-tuned fixed PTQ (2-bit) (ablation)post-training quantization · CIFAR-10 ResNet-20 2-bitTop-1 accuracy (%): 64.34 -> 65.94Improved
add smooth regularizers to full method, activations 8x compression (ablation)Ours · CIFAR-10 ResNet-20 (AC 8)Top-1 accuracy (%): 91.55 -> 91.62No clear effect
add smooth regularizers, activations not quantized (ablation)Ours · CIFAR-10 ResNet-20 (AC 1)Top-1 accuracy (%): 91.75 -> 91.97Improved
add smooth regularizers, activations not quantized (ablation)Ours · CIFAR-10 ResNet-20 (AC 1)model compression ratio: 16.19 -> 14.73Hurt
learned layer for 4-bit vs fixed alternative layer choice (ablation)Ours · Vimeo-90K ESPCNPSNR (dB): 31.10 -> 30.74Improved

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