# Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?

arXiv: https://arxiv.org/abs/2605.25561 · HTML: https://mlsanity.com/paper/2605.25561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 47 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 26 of 26)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Semi-supervised Medical Image Segmentation through Dual-task Consistency](https://mlsanity.com/paper/2009.04448/) (2020)
- [DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation](https://mlsanity.com/paper/1506.06448/) (2015)
- [Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/1903.00348/) (2019)
- [Mutual Consistency Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2109.09960/) (2021)
- [Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency](https://mlsanity.com/paper/2012.07042/) (2020)
- [Annotation-efficient deep learning for automatic medical image segmentation](https://mlsanity.com/paper/2012.04885/) (2020)
- [Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2110.08762/) (2021)
- [Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective](https://mlsanity.com/paper/2302.01735/) (2023)
- [Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2310.11320/) (2023)
- [Uncertainty guided semi-supervised segmentation of retinal layers in OCT images](https://mlsanity.com/paper/2103.02083/) (2021)
- [All-Around Real Label Supervision: Cyclic Prototype Consistency Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2109.13930/) (2021)
- [Uncertainty-Guided Mutual Consistency Learning for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2112.02508/) (2021)
- [Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation](https://mlsanity.com/paper/2110.08589/) (2021)
- [Translation Consistent Semi-supervised Segmentation for 3D Medical Images](https://mlsanity.com/paper/2203.14523/) (2022)
- [Anatomically-aware Uncertainty for Semi-supervised Image Segmentation](https://mlsanity.com/paper/2310.16099/) (2023)
- [Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2311.11686/) (2023)
- [Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2111.10989/) (2021)
- [SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2412.15526/) (2024)
- [Generalizable Pancreas Segmentation via a Dual Self-Supervised Learning Framework](https://mlsanity.com/paper/2505.07165/) (2025)
- [A Dual-Task Synergy-Driven Generalization Framework for Pancreatic Cancer Segmentation in CT Scans](https://mlsanity.com/paper/2505.01644/) (2025)
- [Fully Differentiable Bidirectional Dual-Task Synergistic Learning for Semi-Supervised 3D Medical Image Segmentation](https://mlsanity.com/paper/2602.09378/) (2026)

## Abstract (arXiv)

Semi-supervised learning has become a dominant paradigm for reducing annotation costs. However, we argue that the current progress is clouded by a twofold overconfidence problem. Algorithmically, mainstream pseudo-labeling frameworks often conflate prediction confidence with uncertainty, leading to severe confirmation bias. Strategically, since multiple benchmark datasets lack dedicated validation sets, some studies use the test set for validation as well, leading to inflated performance estimates. Subsequent methods, compelled to employ the same strategy to surpass reported SOTA, trigger an arms race of overfitting. This raises concerns that the impressive numerical gains in the community may reflect overfitting rather than genuine progress. Thus, we propose a tri-space calibrated segmentation framework founded on a principled dual-axis reliability assessment engine. It explicitly decouples confidence from uncertainty and uses this signal to detect and correct confirmation bias across feature, probability, and image spaces in a collaborative manner. Across three benchmark datasets, TCSeg consistently delivers strong performance under existing evaluation protocols. More importantly, we advocate that the community report final-checkpoint results under multiple-run protocols, thereby establishing more rigorous benchmarks with a more realistic perspective. Code will be available: github.com/DirkLiii/TCSeg.