AI Paper Atlas

Research map / Detection and segmentation / CNN features

Unsupervised Local Discrimination for Medical Images

Huai Chen, Renzhen Wang, Xiuying Wang, Jieyu Li, Qu Fang, Hui Li, Jianhao Bai, Qing Peng, Deyu Meng, Lisheng Wang

TPAMI 2023 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 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 hypersphere mixup to patch discrimination (ablation)Pd · Color fundus segmentationDSC (%): 84.19 -> 84.65Improved
add hypersphere mixup to patch discrimination (ablation)Pd · Chest X-ray segmentationDSC (%): 79.98 -> 81.81Improved
add region discrimination to Pd+mix (ablation)Pd+mix · Color fundus segmentationDSC (%): 84.65 -> 85.12Improved
add region discrimination to Pd+mix (ablation)Pd+mix · Chest X-ray segmentationDSC (%): 81.81 -> 82.11Improved
replace IPMI21 center-distance loss with region discrimination lossIPMI21 · Chest X-ray pneumothoraxDSC (%): 41.03 -> 43.20Improved
replace IPMI21 with region discriminationIPMI21 · Color fundus hard exudatesDSC (%): 65.89 -> 67.05Improved
pre-train with Rd instead of training from scratchtiny VGG16 U-Net · Chest X-ray pneumothoraxDSC (%): 34.45 -> 43.20Improved
use region discrimination instead of supervised pre-trainingsupervised pre-trained encoder · Color fundus segmentationDSC (%): 82.64 -> 85.12Improved
increase cluster number from 4 to 16 (ablation)Rd · Color fundus segmentationDSC (%): 84.51 -> 85.12Improved
increase cluster number from 4 to 16 (ablation)Rd · Chest X-ray segmentationDSC (%): 82.33 -> 82.11Hurt
add region discrimination with cluster number C=4 versus C=0 (ablation)Pd+mix · Chest X-ray pneumothoraxDSC (%): 42.36 -> 44.34Improved
increase patch-out size from (8,8) to (16,16) (ablation)Pd+mix · Color fundus segmentationDSC (%)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