# Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space

arXiv: https://arxiv.org/abs/1907.09607 · HTML: https://mlsanity.com/paper/1907.09607/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions](https://mlsanity.com/paper/2303.12484/) (2023)
- [Black-box Few-shot Knowledge Distillation](https://mlsanity.com/paper/2207.12106/) (2022)
- [Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean](https://mlsanity.com/paper/2108.04423/) (2021)
- [Brain Structure-Function Fusing Representation Learning using Adversarial Decomposed-VAE for Analyzing MCI](https://mlsanity.com/paper/2305.14404/) (2023)
- [Semi-Supervised Learning for Eye Image Segmentation](https://mlsanity.com/paper/2103.09369/) (2021)
- [Towards disease-aware image editing of chest X-rays](https://mlsanity.com/paper/2109.01071/) (2021)
- [Conditional Generative Models for Simulation of EMG During Naturalistic Movements](https://mlsanity.com/paper/2211.01856/) (2022)
- [A Comparison of Self-Supervised Pretraining Approaches for Predicting Disease Risk from Chest Radiograph Images](https://mlsanity.com/paper/2306.08955/) (2023)
- [Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification](https://mlsanity.com/paper/2307.15987/) (2023)

## Abstract (arXiv)

The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to encourage consensus among ensemble predictions of unknown labels, improving generalization of the model by making it more insensitive to the latent space. Currently, such an ensemble is obtained by randomization such as dropout regularization and random data augmentation. In this work, we hypothesize -- from the generalization perspective -- that self-ensembling can be improved by exploiting the stochasticity of a disentangled latent space. To this end, we present a stacked SSL model that utilizes unsupervised disentangled representation learning as the stochastic embedding for self-ensembling. We evaluate the presented model for multi-label classification using chest X-ray images, demonstrating its improved performance over related SSL models as well as the interpretability of its disentangled representations.