mlsanityData to 14 Oct 2026

Human-Inspired Asymmetric Collaboration for Dual-Student Semi-Supervised Medical Image Segmentation

arXiv 2610.18133 ↗First posted 13 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Dual-student learning enriches predictive diversity in SSMIS by introducing a strongly augmented view alongside a weakly augmented view. Insufficient strong augmentation may homogenize the students, whereas excessive augmentation can corrupt anatomical evidence and destabilize collaboration. This challenge echoes feedback-regulated human instruction, where learners receive differentiated tasks and the task difficulty is continually adjusted according to their evolving responses. Inspired by these, we propose Human-Inspired Asymmetric Collaboration (HAC), a closed-loop dual-student framework that maintains weak--strong learning through adaptive difficulty calibration and geometry preservation. Specifically, Reinforcement-guided Difficulty Calibration (RDC) formulates strong-augmentation control as a window-level reinforcement learning process, using augmentation history, realized perturbations, and training responses to dynamically adjust the augmentation magnitude, operation number, and magnitude range. Meanwhile, the Gramian Geometry Preservation Constraint (G2PC) preserves the early-stage three-branch geometry through global volume and pairwise area constraints, preventing shared supervision from homogenizing the two students. Comprehensive evaluations across LA, Pancreas, and BraTS-2019 validate both the segmentation effectiveness and capability-aware difficulty calibration of HAC.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

23 of 41 references.

References · 23

  1. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  2. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  3. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  4. 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 379
  5. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 260
  6. 2020Semi-supervised Medical Image Segmentation through Dual-task Consistencycited by 216
  7. 2018Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysiscited by 179
  8. 2015DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentationcited by 159
  9. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 154
  10. 2019Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentationcited by 140
  11. 2023Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentationcited by 116
  12. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 108
11 more
  1. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 100
  2. 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 76
  3. 2024Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentationcited by 30
  4. 2021All-Around Real Label Supervision: Cyclic Prototype Consistency Learning for Semi-supervised Medical Image Segmentationcited by 25
  5. 2023Alternate Diverse Teaching for Semi-supervised Medical Image Segmentationcited by 22
  6. 2020Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentationcited by 17
  7. 2024DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image Segmentationcited by 15
  8. 2020Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentationcited by 8
  9. 2019Adversarial Policy Gradient for Deep Learning Image Augmentationcited by 5
  10. 2026Bidirectional Channel-selective Semantic Interaction for Semi-Supervised Medical Segmentationcited by 3
  11. 2025DualFete: Revisiting Teacher-Student Interactions from a Feedback Perspective for Semi-supervised Medical Image Segmentationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Knowledge Transferring with Switching Dual-Student Framework for Semi-Supervised Medical Image Segmentation
  2. 2025J-RAS: Mutual Adaptation for Medical Image Segmentation via Contrastive Retrieval-Augmented Joint Optimization
  3. 2026Active few-shot segmentation by reinforcing data selection
  4. 2022ACT-Net: Asymmetric Co-Teacher Network for Semi-supervised Memory-efficient Medical Image Segmentation
  5. 2023Cross-head mutual Mean-Teaching for semi-supervised medical image segmentation
  6. 2025DuetMatch: Harmonizing Semi-Supervised Brain MRI Segmentation via Decoupled Branch Optimization
  7. 2026Camyla: Scaling Autonomous Research in Medical Image Segmentation
  8. 2026MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning