AI Paper Atlas

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

Reducing Domain Gap in Frequency and Spatial Domain for Cross-Modality Domain Adaptation on Medical Image Segmentation

Shaolei Liu, Siqi Yin, Linhao Qu, Manning Wang

AAAI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-modality medical segmentation adaptation · 17 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
combine frequency and spatial transfer teachers through multi-teacher distillation (ablation)TransUNet UDA · Abdominal multi-organDice: 88.4 -> 89.2Improved
combine frequency and spatial transfer teachers through multi-teacher distillation (ablation)TransUNet UDA · CardiacDice: 83.9 -> 85.3Improved
use frequency transfer instead of no adaptation (ablation)TransUNet UDA · Abdominal multi-organDice: 53.3 -> 87.3Improved
use frequency transfer instead of no adaptation (ablation)TransUNet UDA · CardiacDice: 46.0 -> 84.6Improved
use spatial histogram transfer instead of no adaptation (ablation)TransUNet UDA · Abdominal multi-organDice: 53.3 -> 88.6Improved
use spatial histogram transfer instead of no adaptation (ablation)TransUNet UDA · CardiacDice: 46.0 -> 83.7Improved
mix spatial- and frequency-transferred images in one model instead of using multi-teacher distillation (ablation)TransUNet UDA · Abdominal multi-organDice: 89.2 -> 88.4Hurt
mix spatial- and frequency-transferred images in one model instead of using multi-teacher distillation (ablation)TransUNet UDA · CardiacDice: 85.3 -> 83.9Hurt
use batch momentum histogram matching instead of whole-domain histogram matching (ablation)Spatial transfer · CardiacDice: 81.5 -> 83.7Improved
use batch momentum histogram matching instead of single-image histogram matching (ablation)Spatial transfer · CardiacDice: 82.8 -> 83.7Improved
use batch momentum histogram matching instead of current-batch average matching (ablation)Spatial transfer · CardiacDice: 83.4 -> 83.7Improved
retain low-frequency FC [0,1] and third-layer FC [7,14], replacing other source frequency components with target components (ablation)NSCT frequency transfer · Cardiac synthetic target validationDice: 60.42 -> 64.85Improved

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