AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Lossy and Lossless (L2) Post-training Model Size Compression

Yumeng Shi, Shihao Bai, Xiuying Wei, Ruihao Gong, Jianlei Yang

ICCV 2023 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 7 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 pruning to quantization (joint pruning and quantization transformation) at 20x compression (ablation)L2 compression · ImageNet-1k val, ResNet-18 at ~20x CRTop-1 accuracy (%): 68.34% (linear quant) -> 69.15%Improved
use joint pruning and quantization instead of single quantization at ~15x CR (ablation)L2 compression · ImageNet-1k val, ResNet-18 at ~15x CRTop-1 accuracy (%): 70.37% (linear) vs 70.20% (joint)No clear effect
vary kernel function (cosine, linear, triangle) and resolution (16-128) of the differentiable counter (ablation)L2 compression · ImageNet-1k val, ResNet-18 at 15x CRTop-1 accuracy (%): 70.04% to 70.25%No clear effect
use range coding instead of Huffman coding (ablation)L2 compression · ResNet-18 compressed sizemodel size (KB): 2500.24KB -> 2288.99KB (smallest target)Improved
increase calibration set from 256 to 768+ images (ablation)L2 compression · ImageNet-1k val, ResNet-18 at 12x CRTop-1 accuracy (%): 67.93 -> 70.75 (768 images)Improved
increase calibration set from 1000 to 2000 images (ablation)L2 compression · ImageNet-1k val, ResNet-18 at 12x CRTop-1 accuracy (%): 70.79 -> 70.78No clear effect
add weight fine-tuning after transformation training (ablation)L2 compression · ImageNet-1k val, ResNet-18 at ~10x CRTop-1 accuracy (%): 70.47% (no fine-tune, 10.05x) vs 70.79% (12x with fine-tune)No clear effect
apply L2 compression versus AdaRound at similar/higher CRMobileNetV2 · ImageNet-1k valTop-1 accuracy (%): 69.01% -> 71.53%Improved
increase target CR on ViT-base from 6x to 14x (ablation)L2 compression · ImageNet-1k val, ViT-base-patch16Top-1 accuracy (%): 84.97% -> 81.86%Hurt

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