mlsanityData to 7 Oct 2026

Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder

arXiv 2105.00026 ↗First posted 30 Apr 2021stat.ML cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a new method to perform data augmentation in a reliable way in the High Dimensional Low Sample Size (HDLSS) setting using a geometry-based variational autoencoder. Our approach combines a proper latent space modeling of the VAE seen as a Riemannian manifold with a new generation scheme which produces more meaningful samples especially in the context of small data sets. The proposed method is tested through a wide experimental study where its robustness to data sets, classifiers and training samples size is stressed. It is also validated on a medical imaging classification task on the challenging ADNI database where a small number of 3D brain MRIs are considered and augmented using the proposed VAE framework. In each case, the proposed method allows for a significant and reliable gain in the classification metrics. For instance, balanced accuracy jumps from 66.3% to 74.3% for a state-of-the-art CNN classifier trained with 50 MRIs of cognitively normal (CN) and 50 Alzheimer disease (AD) patients and from 77.7% to 86.3% when trained with 243 CN and 210 AD while improving greatly sensitivity and specificity metrics.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 58 of its 141 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

58 of 141 references.

References · 58

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  10. 2016Deep Variational Information Bottleneckcited by 915
  11. 2017Wasserstein GANcited by 635
  12. 2015Importance Weighted Autoencoderscited by 454
38 more
  1. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 324
  2. 2017Data Augmentation Generative Adversarial Networkscited by 278
  3. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  4. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  5. 2017VAE with a VampPriorcited by 247
  6. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  7. 2017Advances in Variational Inferencecited by 236
  8. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  9. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  10. 2019Diagnosing and Enhancing VAE Modelscited by 192
  11. 2018Hyperspherical Variational Auto-Encoderscited by 188
  12. 2016Variational Lossy Autoencodercited by 175
  13. 2017Latent Space Oddity: on the Curvature of Deep Generative Modelscited by 169
  14. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 146
  15. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  16. 2019From Variational to Deterministic Autoencoderscited by 131
  17. 2019Continuous Hierarchical Representations with Poincar'e Variational Auto-Encoderscited by 111
  18. 2019Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluationcited by 106
  19. 2020Learning Latent Space Energy-Based Prior Modelcited by 104
  20. 2018BAGAN: Data Augmentation with Balancing GANcited by 90
  21. 2017The Riemannian Geometry of Deep Generative Modelscited by 81
  22. 2018How good is my GAN?cited by 74
  23. 2018Explorations in Homeomorphic Variational Auto-Encodingcited by 65
  24. 2021CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detectioncited by 64
  25. 2018Resampled Priors for Variational Autoencoderscited by 56
  26. 2017Metrics for Deep Generative Modelscited by 53
  27. 2019Learning Hierarchical Priors in VAEscited by 53
  28. 2020Geometrically Enriched Latent Spacescited by 45
  29. 2018Hamiltonian Variational Auto-Encodercited by 41
  30. 2018DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GANcited by 34
  31. 2020Variational Autoencoders with Riemannian Brownian Motion Priorscited by 34
  32. 2017Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentationcited by 27
  33. 2016A Locally Adaptive Normal Distributioncited by 23
  34. 2019A Contrastive Divergence for Combining Variational Inference and MCMCcited by 20
  35. 2018Conditional Infilling GANs for Data Augmentation in Mammogram Classificationcited by 19
  36. 2019FMRI data augmentation via synthesiscited by 19
  37. 2017Synthesis of Positron Emission Tomography (PET) Images via Multi-channel Generative Adversarial Networks (GANs)cited by 18
  38. 2018Generating Highly Realistic Images of Skin Lesions with GANscited by 16

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 6; 2025: 3; 2026: 4.

27 papers.

Sort:

By area:

  1. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  2. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  3. 2022A Geometric Perspective on Variational Autoencoderscited by 24
  4. 2023A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Modelscited by 17
  5. 2023Auditing and Generating Synthetic Data with Controllable Trust Trade-offscited by 13
  6. 2023VTAE: Variational Transformer Autoencoder with Manifolds Learningcited by 10
  7. 2024Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspectivecited by 6
  8. 2024A probabilistic framework for learning non-intrusive corrections to long-time climate simulations from short-time training datacited by 5
  9. 2023Improving Joint Speech-Text Representations Without Alignmentcited by 4
  10. 2023MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformationscited by 4
  11. 2024Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimescited by 3
  12. 2024Current Symmetry Group Equivariant Convolution Frameworks for Representation Learningcited by 2
15 more
  1. 2025Hyperbolic Dual Feature Augmentation for Open-Environmentcited by 2
  2. 2022XADLiME: eXplainable Alzheimer's Disease Likelihood Map Estimation via Clinically-guided Prototype Learningcited by 1
  3. 2023Improving Multimodal Joint Variational Autoencoders through Normalizing Flows and Correlation Analysiscited by 1
  4. 2023Unified High-binding Watermark for Unconditional Image Generation Modelscited by 1
  5. 2024On Probabilistic Pullback Metrics for Latent Hyperbolic Manifoldscited by 1
  6. 2025Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Modelscited by 1
  7. 2025Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modelingcited by 1
  8. 2026PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learningcited by 1
  9. 2023Variational Inference for Longitudinal Data Using Normalizing Flowscited by 0
  10. 2023Use the Detection Transformer as a Data Augmentercited by 0
  11. 2023Sampling From Autoencoders' Latent Space via Quantization And Probability Mass Function Conceptscited by 0
  12. 2024Pseudo-Nonlinear Data Augmentation: A Constrained Energy Minimization Viewpointcited by 0
  13. 2026An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectoriescited by 0
  14. 2026Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steeringcited by 0
  15. 2026Task-Induced Riemannian Metrics for Vision Transformer Feature Spacescited by 0