mlsanityData to 7 Oct 2026

Data Augmentation with Variational Autoencoders and Manifold Sampling

arXiv 2103.13751 ↗First posted 25 Mar 2021stat.ML cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

We propose a new efficient way to sample from a Variational Autoencoder in the challenging low sample size setting. This method reveals particularly well suited to perform data augmentation in such a low data regime and is validated across various standard and real-life data sets. In particular, this scheme allows to greatly improve classification results on the OASIS database where balanced accuracy jumps from 80.7% for a classifier trained with the raw data to 88.6% when trained only with the synthetic data generated by our method. Such results were also observed on 3 standard data sets and with other classifiers. A code is available at https://github.com/clementchadebec/Data_Augmentation_with_VAE-DALI.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 8 of its 22 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

8 of 22 references.

References · 8

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2017Data Augmentation Generative Adversarial Networkscited by 278
  5. 2017VAE with a VampPriorcited by 247
  6. 2017Latent Space Oddity: on the Curvature of Deep Generative Modelscited by 169
  7. 2017Data Augmentation in Emotion Classification Using Generative Adversarial Networkscited by 19
  8. 2020Geometry-Aware Hamiltonian Variational Auto-Encodercited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 4; 2025: 2; 2026: 2.

16 papers.

Sort:

  1. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  2. 2024Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimescited by 8
  3. 2023RDA-INR: Riemannian Diffeomorphic Autoencoding via Implicit Neural Representationscited by 7
  4. 2023Anchor Data Augmentationcited by 5
  5. 2023MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformationscited by 4
  6. 2023SAVAE: Leveraging the variational Bayes autoencoder for survival analysiscited by 4
  7. 2023D3A-TS: Denoising-Driven Data Augmentation in Time Seriescited by 3
  8. 2024Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimescited by 3
  9. 2024A Survey on the Integration of Generative AI for Critical Thinking in Mobile Networkscited by 1
  10. 2026Riemannian Geometry-Preserving Variational Autoencoder for MI-BCI Data Augmentationcited by 1
  11. 2023Improving the Security of Smartwatch Payment with Deep Learningcited by 0
  12. 2023Collinear datasets augmentation using Procrustes validation setscited by 0
4 more
  1. 2024Evaluating the Stability of Deep Learning Latent Feature Spacescited by 0
  2. 2025FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theorycited by 0
  3. 2025Data-driven Prediction of Species-Specific Plant Responses to Spectral-Shifting Films from Leaf Phenotypic and Photosynthetic Traitscited by 0
  4. 2026Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoderscited by 0