# MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformations

arXiv: https://arxiv.org/abs/2312.13440 · HTML: https://mlsanity.com/paper/2312.13440/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 95 references that are in the map.
- First posted on arXiv 20 Dec 2023.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders](https://mlsanity.com/paper/1611.02648/) (2016)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces](https://mlsanity.com/paper/1903.03545/) (2019)
- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [Data augmentation using learned transformations for one-shot medical image segmentation](https://mlsanity.com/paper/1902.09383/) (2019)
- [BAGAN: Data Augmentation with Balancing GAN](https://mlsanity.com/paper/1803.09655/) (2018)

## Built on by (most cited first, 4 of 4)

- [Invariant Shape Representation Learning For Image Classification](https://mlsanity.com/paper/2411.12201/) (2024)
- [CoRLD: Contrastive Representation Learning Of Deformable Shapes In Images](https://mlsanity.com/paper/2503.17162/) (2025)
- [Learning Group Actions In Disentangled Latent Image Representations](https://mlsanity.com/paper/2512.04015/) (2025)
- [Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generation](https://mlsanity.com/paper/2609.08153/) (2026)

## Abstract (arXiv)

Geometric transformations have been widely used to augment the size of training images. Existing methods often assume a unimodal distribution of the underlying transformations between images, which limits their power when data with multimodal distributions occur. In this paper, we propose a novel model, Multimodal Geometric Augmentation (MGAug), that for the first time generates augmenting transformations in a multimodal latent space of geometric deformations. To achieve this, we first develop a deep network that embeds the learning of latent geometric spaces of diffeomorphic transformations (a.k.a. diffeomorphisms) in a variational autoencoder (VAE). A mixture of multivariate Gaussians is formulated in the tangent space of diffeomorphisms and serves as a prior to approximate the hidden distribution of image transformations. We then augment the original training dataset by deforming images using randomly sampled transformations from the learned multimodal latent space of VAE. To validate the efficiency of our model, we jointly learn the augmentation strategy with two distinct domain-specific tasks: multi-class classification on 2D synthetic datasets and segmentation on real 3D brain magnetic resonance images (MRIs). We also compare MGAug with state-of-the-art transformation-based image augmentation algorithms. Experimental results show that our proposed approach outperforms all baselines by significantly improved prediction accuracy. Our code is publicly available at https://github.com/tonmoy-hossain/MGAug.