AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Fine-Grained Data Distribution Alignment for Post-Training Quantization

Yunshan Zhong, Mingbao Lin, Mengzhao Chen, Ke Li, Yunhang Shen, Fei Chao, Yongjian Wu, Rongrong Ji

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 15 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 real calibration dataset to synthetic data (ablation)GDFQ · ImageNet val (ResNet-18, W4A4 all layers)top-1 accuracy (%): 60.60 -> 65.64Improved
add fine-grained BNS alignment (BNS-centralized and BNS-distorted losses) (ablation)GDFQ + C · ImageNet val (ResNet-18, W4A4 all layers)top-1 accuracy (%): 65.64 -> 68.88Improved
use predicted labels instead of real labels for calibration images (ablation)FDDA · ImageNet val (ResNet-18, W4A4 all layers)top-1 accuracy (%): 68.88 -> 68.68No clear effect
FDDA versus best zero-shot method with calibration data (DSG)FDDA · ImageNet val (ResNet-18, W4A4 all layers)top-1 accuracy (%): 66.83 -> 68.88Improved
FDDA versus BRECQ at W4A4 F4L4 on MobileNetV1FDDA · ImageNet val (W4A4, F4L4)top-1 accuracy (%): 57.11 -> 63.75Improved
FDDA versus BRECQ at W4A4 F8L8 on MobileNetV2FDDA · ImageNet val (W4A4, F8L8)top-1 accuracy (%): 66.57 -> 69.32Improved
FDDA versus BRECQ at W5A5 F8L8 on ResNet-18FDDA · ImageNet val (W5A5, F8L8)top-1 accuracy (%): 70.60 -> 70.86Improved
reduce available calibration classes to 700 (ablation)FDDA · ImageNet val (ResNet-18, W4A4 all layers)top-1 accuracy (%): 68.09Hurt
FDDA with only 700 classes versus BRECQFDDA · ImageNet val (ResNet-18, W4A4 all layers)top-1 accuracy (%): 67.94 -> 68.09Improved

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