AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration

Ziqi Zhou, Lei Qi, Yinghuan Shi

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-modality medical segmentation adaptation

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 RAM and DSIR to baselineUNet DeepAll · FundusDice (%): 85.63 -> 88.94Improved
add RAM and DSIR to baselineUNet DeepAll · ProstateDice (%): 84.04 -> 88.08Improved
add RAM and DSIR to baselineUNet DeepAll · ProstateASD (voxel): 2.92 -> 1.37Improved
add RAM style augmentation (ablation)UNet DeepAll · FundusDice (%): 85.63 -> 87.75Improved
add RAM style augmentation (ablation)UNet DeepAll · ProstateDice (%): 84.04 -> 87.27Improved
add DSIR restoration decoder (ablation)UNet DeepAll · FundusDice (%): 85.63 -> 87.21Improved
add DSIR restoration decoder (ablation)UNet DeepAll · ProstateDice (%): 84.04 -> 85.07Improved
add DSIR on top of RAM augmentation (ablation)RAM · FundusDice (%): 87.75 -> 88.94Improved
add DSIR on top of RAM augmentation (ablation)RAM · ProstateDice (%): 87.27 -> 88.08Improved
add semantic consistency loss (ablation)RAM+DSIR · Fundus and ProstateDice (%)Improved
use KL-divergence instead of MSE for consistency (ablation)RAM+DSIR · FundusDice (%): 88.65 -> 88.94No clear effect
use KL-divergence instead of JS-Div for consistency (ablation)RAM+DSIR · FundusDice (%): 88.19 -> 88.94No clear effect

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