# Semi-Supervised and Task-Driven Data Augmentation

arXiv: https://arxiv.org/abs/1902.05396 · HTML: https://mlsanity.com/paper/1902.05396/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2019.

## Built on by (most cited first, 30 of 40)

- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/2207.14191/) (2022)
- [CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision](https://mlsanity.com/paper/2203.01475/) (2022)
- [Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts](https://mlsanity.com/paper/2109.04379/) (2021)
- [Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation](https://mlsanity.com/paper/2109.07407/) (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)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation](https://mlsanity.com/paper/2108.03429/) (2021)
- [Anatomy-aware and acquisition-agnostic joint registration with SynthMorph](https://mlsanity.com/paper/2301.11329/) (2023)
- [Modeling the Probabilistic Distribution of Unlabeled Data forOne-shot Medical Image Segmentation](https://mlsanity.com/paper/2102.02033/) (2021)
- [A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data](https://mlsanity.com/paper/2110.09260/) (2021)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization](https://mlsanity.com/paper/2103.04813/) (2021)
- [Addressing Class Imbalance in Semi-supervised Image Segmentation: A Study on Cardiac MRI](https://mlsanity.com/paper/2209.00123/) (2022)
- [A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources](https://mlsanity.com/paper/2203.07018/) (2022)
- [3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis](https://mlsanity.com/paper/2205.08887/) (2022)
- [Anatomically-aware Uncertainty for Semi-supervised Image Segmentation](https://mlsanity.com/paper/2310.16099/) (2023)
- [Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training](https://mlsanity.com/paper/2103.16493/) (2021)
- [Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation](https://mlsanity.com/paper/2110.02117/) (2021)
- [Learning Morphological Feature Perturbations for Calibrated Semi-Supervised Segmentation](https://mlsanity.com/paper/2203.10196/) (2022)
- [METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopy](https://mlsanity.com/paper/2104.10993/) (2021)
- [Dual-Teacher++: Exploiting Intra-domain and Inter-domain Knowledge with Reliable Transfer for Cardiac Segmentation](https://mlsanity.com/paper/2101.02375/) (2021)
- [Generative appearance replay for continual unsupervised domain adaptation](https://mlsanity.com/paper/2301.01211/) (2023)
- [ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation](https://mlsanity.com/paper/2301.04882/) (2023)
- [Contrastive-mixup learning for improved speaker verification](https://mlsanity.com/paper/2202.10672/) (2022)
- [Segmentation with mixed supervision: Confidence maximization helps knowledge distillation](https://mlsanity.com/paper/2109.10902/) (2021)
- [Leveraging Labeling Representations in Uncertainty-based Semi-supervised Segmentation](https://mlsanity.com/paper/2203.05682/) (2022)
- [IDEAL: Improved DEnse locAL Contrastive Learning for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2210.15075/) (2022)
- [CG-3DSRGAN: A classification guided 3D generative adversarial network for image quality recovery from low-dose PET images](https://mlsanity.com/paper/2304.00725/) (2023)

## Abstract (arXiv)

Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations from clinical experts is expensive and time-consuming. One way to address scarcity of annotated examples is data augmentation using random spatial and intensity transformations. Recently, it has been proposed to use generative models to synthesize realistic training examples, complementing the random augmentation. So far, these methods have yielded limited gains over the random augmentation. However, there is potential to improve the approach by (i) explicitly modeling deformation fields (non-affine spatial transformation) and intensity transformations and (ii) leveraging unlabelled data during the generative process. With this motivation, we propose a novel task-driven data augmentation method where to synthesize new training examples, a generative network explicitly models and applies deformation fields and additive intensity masks on existing labelled data, modeling shape and intensity variations, respectively. Crucially, the generative model is optimized to be conducive to the task, in this case segmentation, and constrained to match the distribution of images observed from labelled and unlabelled samples. Furthermore, explicit modeling of deformation fields allow synthesizing segmentation masks and images in exact correspondence by simply applying the generated transformation to an input image and the corresponding annotation. Our experiments on cardiac magnetic resonance images (MRI) showed that, for the task of segmentation in small training data scenarios, the proposed method substantially outperforms conventional augmentation techniques.