AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

DualFete: Revisiting Teacher-Student Interactions from a Feedback Perspective for Semi-supervised Medical Image Segmentation

Le Yi, Wei Huang, Lei Zhang, Kefu Zhao, Yan Wang, Zizhou Wang

AAAI 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical segmentation · 1 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 dual-teacher feedback (agreement+disagreement) to cross-supervised teachers, full student (ablation)DualFete student · LA 20% labelsDice (%): 91.10 -> 91.89Improved
add feedback loss to cross-supervised dual teacher (ablation)DualFete student · Pancreas 20% labelsDice (%): 82.17 -> 83.49Improved
add cross-supervision between two teachers (ablation)teacher-student with labeled loss · LA 20% labelsDice (%): 88.55 -> 90.30Improved
add single-teacher feedback to baseline teacher-student (ablation)teacher-student · Pancreas 20% labelsDice (%): 77.18 -> 79.27Improved
go from single-teacher to dual-teacher feedback with matched attributors and receivers (ablation)DualFete · Pancreas 20% labelsDice (%): 79.27 -> 81.12Improved
mismatch feedback attributors and receivers (ablation)dual-teacher DualFete · LA 20% labelsDice (%): 90.89 -> 87.69Hurt
use strong-augmentation likelihood in feedback loss (ablation)dual-teacher DualFete · LA 20% labelsDice (%): 90.89 -> 90.14Hurt
use feedback loss alone without cross-supervision (ablation)dual-teacher DualFete · Pancreas 20% labelsDice under strong-augmentation perturbation: 78.42 -> 57.40 (teacher phi)Hurt
fine-tune the student on labeled data (w.ft.) (ablation)DualFete · LA 5% and 10% labelsDice (%): 90.35 -> 90.22 (LA 5%); Pancreas 20%: 83.49 -> 83.85Mixed
use DualFete instead of AD-MTDualFete · Pancreas 10% labelsDice (%): 80.21 -> 81.99Improved
use DualFete instead of TraCoCoDualFete · BraTS 20% labelsDice (%): 86.69 -> 85.83Hurt
set confidence threshold of cross-supervised loss to 0.7 (ablation)DualFete · LA and PancreasDice (%)Improved

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