# Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization

arXiv: https://arxiv.org/abs/2103.04813 · HTML: https://mlsanity.com/paper/2103.04813/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 60 references that are in the map.
- First posted on arXiv 8 Mar 2021.

## Builds on (most cited first, 30 of 42)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Formal Limitations on the Measurement of Mutual Information](https://mlsanity.com/paper/1811.04251/) (2018)
- [Learning Discrete Representations via Information Maximizing Self-Augmented Training](https://mlsanity.com/paper/1702.08720/) (2017)
- [Understanding the Limitations of Variational Mutual Information Estimators](https://mlsanity.com/paper/1910.06222/) (2019)
- [Data augmentation using learned transformations for one-shot medical image segmentation](https://mlsanity.com/paper/1902.09383/) (2019)
- [Data Distillation: Towards Omni-Supervised Learning](https://mlsanity.com/paper/1712.04440/) (2017)
- [Unsupervised domain adaptation for medical imaging segmentation with self-ensembling](https://mlsanity.com/paper/1811.06042/) (2018)
- [Boosting Self-Supervised Learning via Knowledge Transfer](https://mlsanity.com/paper/1805.00385/) (2018)
- [AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data](https://mlsanity.com/paper/1901.04596/) (2019)
- [Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations](https://mlsanity.com/paper/1911.01218/) (2019)
- [Learning Image Representations by Completing Damaged Jigsaw Puzzles](https://mlsanity.com/paper/1802.01880/) (2018)
- [Deep Co-Training for Semi-Supervised Image Segmentation](https://mlsanity.com/paper/1903.11233/) (2019)
- [Multimodal Self-Supervised Learning for Medical Image Analysis](https://mlsanity.com/paper/1912.05396/) (2019)
- [Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model](https://mlsanity.com/paper/1903.01248/) (2019)

## Built on by (most cited first, 14 of 14)

- [Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2110.08762/) (2021)
- [Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation](https://mlsanity.com/paper/2112.09645/) (2021)
- [Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels](https://mlsanity.com/paper/2107.13741/) (2021)
- [Prompt Tuning for Parameter-efficient Medical Image Segmentation](https://mlsanity.com/paper/2211.09233/) (2022)
- [An Embarrassingly Simple Consistency Regularization Method for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2202.00677/) (2022)
- [Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity](https://mlsanity.com/paper/2302.02125/) (2023)
- [Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation](https://mlsanity.com/paper/2310.01680/) (2023)
- [Segmentation with mixed supervision: Confidence maximization helps knowledge distillation](https://mlsanity.com/paper/2109.10902/) (2021)
- [MaNi: Maximizing Mutual Information for Nuclei Cross-Domain Unsupervised Segmentation](https://mlsanity.com/paper/2206.14437/) (2022)
- [Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation](https://mlsanity.com/paper/2202.02371/) (2022)
- [Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation](https://mlsanity.com/paper/2302.03296/) (2023)
- [Representation Learning with Information Theory for COVID-19 Detection](https://mlsanity.com/paper/2207.01437/) (2022)
- [Convolutional Neural Network Model for Diabetic Retinopathy Feature Extraction and Classification](https://mlsanity.com/paper/2310.10806/) (2023)
- [Diversified Multi-prototype Representation for Semi-supervised Segmentation](https://mlsanity.com/paper/2111.08651/) (2021)

## Abstract (arXiv)

The scarcity of labeled data often impedes the application of deep learning to the segmentation of medical images. Semi-supervised learning seeks to overcome this limitation by exploiting unlabeled examples in the learning process. In this paper, we present a novel semi-supervised segmentation method that leverages mutual information (MI) on categorical distributions to achieve both global representation invariance and local smoothness. In this method, we maximize the MI for intermediate feature embeddings that are taken from both the encoder and decoder of a segmentation network. We first propose a global MI loss constraining the encoder to learn an image representation that is invariant to geometric transformations. Instead of resorting to computationally-expensive techniques for estimating the MI on continuous feature embeddings, we use projection heads to map them to a discrete cluster assignment where MI can be computed efficiently. Our method also includes a local MI loss to promote spatial consistency in the feature maps of the decoder and provide a smoother segmentation. Since mutual information does not require a strict ordering of clusters in two different assignments, we incorporate a final consistency regularization loss on the output which helps align the cluster labels throughout the network. We evaluate the method on four challenging publicly-available datasets for medical image segmentation. Experimental results show our method to outperform recently-proposed approaches for semi-supervised segmentation and provide an accuracy near to full supervision while training with very few annotated images.