# Transductive image segmentation: Self-training and effect of uncertainty estimation

arXiv: https://arxiv.org/abs/2107.08964 · HTML: https://mlsanity.com/paper/2107.08964/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 19 Jul 2021.

## Builds on (most cited first, 11 of 11)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation](https://mlsanity.com/paper/1603.05959/) (2016)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model](https://mlsanity.com/paper/1903.01248/) (2019)
- [Transductive Information Maximization For Few-Shot Learning](https://mlsanity.com/paper/2008.11297/) (2020)
- [Curriculum semi-supervised segmentation](https://mlsanity.com/paper/1904.05236/) (2019)
- [A New Ensemble Learning Framework for 3D Biomedical Image Segmentation](https://mlsanity.com/paper/1812.03945/) (2018)

## Built on by (most cited first, 1 of 1)

- [DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging](https://mlsanity.com/paper/2506.09024/) (2025)

## Abstract (arXiv)

Semi-supervised learning (SSL) uses unlabeled data during training to learn better models. Previous studies on SSL for medical image segmentation focused mostly on improving model generalization to unseen data. In some applications, however, our primary interest is not generalization but to obtain optimal predictions on a specific unlabeled database that is fully available during model development. Examples include population studies for extracting imaging phenotypes. This work investigates an often overlooked aspect of SSL, transduction. It focuses on the quality of predictions made on the unlabeled data of interest when they are included for optimization during training, rather than improving generalization. We focus on the self-training framework and explore its potential for transduction. We analyze it through the lens of Information Gain and reveal that learning benefits from the use of calibrated or under-confident models. Our extensive experiments on a large MRI database for multi-class segmentation of traumatic brain lesions shows promising results when comparing transductive with inductive predictions. We believe this study will inspire further research on transductive learning, a well-suited paradigm for medical image analysis.