arXiv:2511.09319v1 Announce Type: new 
Abstract: The teacher-student paradigm has emerged as a canonical framework in semi-supervised learning. When applied to medical image segmentation, the paradigm faces challenges due to inherent image ambiguities, making it particularly vulnerable to erroneous supervision. Crucially, the student's iterative reconfirmation of these errors leads to self-reinforcing bias. While some studies attempt to mitigate this bias, they often rely on external modifications to the conventional teacher-student framework, overlooking its intrinsic potential for error correction. In response, this work introduces a feedback mechanism into the teacher-student framework to counteract error reconfirmations. Here, the student provides feedback on the changes induced by the teacher's pseudo-labels, enabling the teacher to refine these labels accordingly. We specify that this interaction hinges on two key components: the feedback attributor, which designates pseudo-labels triggering the student's update, and the feedback receiver, which determines where to apply this feedback. Building on this, a dual-teacher feedback model is further proposed, which allows more dynamics in the feedback loop and fosters more gains by resolving disagreements through cross-teacher supervision while avoiding consistent errors. Comprehensive evaluations on three medical image benchmarks demonstrate the method's effectiveness in addressing error propagation in semi-supervised medical image segmentation.

تقدم المقالة آلية جديدة للتغذية الراجعة ضمن نموذج المعلم-الطالب لعملية تقسيم الصور الطبية شبه المشروطة. تتناول هذه الطريقة التحديات مثل الإشراف الخاطئ والانحياز المعزز ذاتيًا من خلال السماح للطلاب بتقديم ملاحظات حول التسميات الزائفة التي أنشأها المعلم. النموذج المقترح للتغذية الراجعة من معلمين يعزز هذه التفاعلات، بهدف تحسين الدقة في مهام التصوير الطبي.

El artículo presenta un nuevo mecanismo de retroalimentación dentro del paradigma de maestro-alumno para la segmentación de imágenes médicas semi-supervisada. Este enfoque aborda desafíos como la supervisión errónea y el sesgo auto-reforzante al permitir que los estudiantes proporcionen comentarios sobre las pseudo-etiquetas generadas por el maestro. El modelo de retroalimentación de doble maestro propuesto mejora esta interacción, con el objetivo de mejorar la precisión en las tareas de imagen médica.

L'article présente un nouveau mécanisme de rétroaction au sein du paradigme enseignant-étudiant pour la segmentation d'images médicales semi-supervisée. Cette approche aborde des défis tels que la supervision erronée et le biais auto-renforçant en permettant aux étudiants de fournir des retours sur les pseudo-étiquettes générées par l'enseignant. Le modèle de rétroaction à double enseignant proposé améliore cette interaction, visant à améliorer la précision dans les tâches d'imagerie médicale.

The article introduces a novel feedback mechanism within the teacher-student paradigm for semi-supervised medical image segmentation. This approach addresses challenges such as erroneous supervision and self-reinforcing bias by allowing students to provide feedback on teacher-generated pseudo-labels. The proposed dual-teacher feedback model enhances this interaction, aiming to improve accuracy in medical imaging tasks.

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

Was this article worth reading? Share it

Feedhunt

TheQuizMaster

Customer Feedback

Feeedback

ClassX

One More Thing in AI

Ready to build your own newsroom?