AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation

Xiaowei Xu, Qing Lu, Lin Yang, Sharon Hu, Danny Chen, Yu Hu, Yiyu Shi

CVPR 2018 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 104 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 INQ-7bit quantization to suggestive annotation and network trainingSuggestive annotation pipeline with five FCNs · MICCAI Gland Part AF1 score: 0.921 -> 0.930Improved
Add INQ-7bit quantization to suggestive annotation and network trainingSuggestive annotation pipeline with five FCNs · MICCAI Gland Part AObject Dice: 0.904 -> 0.914Improved
Add INQ-7bit quantization to suggestive annotation and network trainingSuggestive annotation pipeline with five FCNs · MICCAI Gland Part BF1 score: 0.855 -> 0.862Improved
Add INQ-7bit quantization to suggestive annotation and network trainingSuggestive annotation pipeline with five FCNs · MICCAI Gland Part BObject Dice: 0.858 -> 0.859Improved
Add INQ-7bit quantization to suggestive annotation and network trainingSuggestive annotation pipeline with five FCNs · MICCAI Gland Part AObject Hausdorff: 44.736 -> 41.783Improved
Add INQ-7bit quantization to suggestive annotation and network trainingSuggestive annotation pipeline with five FCNs · MICCAI Gland Part BObject Hausdorff: 96.976 -> 97.390Hurt
Use INQ-7bit instead of floating-point or INQ-5bit quantization (ablation)Suggestive annotation FCNs · MICCAI GlandaccuracyImproved
Quantize network training rather than train with floating-point representation (ablation)Segmentation FCNs · MICCAI GlandaccuracyHurt
Use INQ with 3 bits, DoReFa-Net, or TWN instead of floating point (ablation)Segmentation FCNs · MICCAI Gland validationaccuracyHurt
Vary the number of parallel suggestive FCNs (ablation)Suggestive annotation · MICCAI GlandaccuracyMixed
Add quantization to suggestive annotation (ablation)Suggestive annotation FCNs · MICCAI GlanduncertaintyImproved

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