mlsanityData to 7 Oct 2026

Dropout as data augmentation

arXiv 1506.08700 ↗First posted 29 Jun 2015stat.ML cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present an approach to projecting the dropout noise within a network back into the input space, thereby generating augmented versions of the training data, and we show that training a deterministic network on the augmented samples yields similar results. Finally, we propose a new dropout noise scheme based on our observations and show that it improves dropout results without adding significant computational cost.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 8; 2023: 8; 2024: 4; 2025: 3; 2026: 1.

27 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2021Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoderscited by 88
  3. 2021Reflash Dropout in Image Super-Resolutioncited by 41
  4. 2021Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Predictioncited by 36
  5. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  6. 2022The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspectivecited by 24
  7. 2023SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectivescited by 15
  8. 2022A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Momentscited by 14
  9. 2023Rethinking Data Distillation: Do Not Overlook Calibrationcited by 13
  10. 2024RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classificationcited by 12
  11. 2022Tackling covariate shift with node-based Bayesian neural networkscited by 8
  12. 2023CoReFace: Sample-Guided Contrastive Regularization for Deep Face Recognitioncited by 7
15 more
  1. 2023Anchor Data Augmentationcited by 5
  2. 2022A Survey on Dropout Methods and Experimental Verification in Recommendationcited by 4
  3. 2024ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videoscited by 3
  4. 2022Frequency Dropout: Feature-Level Regularization via Randomized Filteringcited by 2
  5. 2025Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approachcited by 2
  6. 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reductioncited by 1
  7. 2023Deep Augmentation: Dropout as Augmentation for Self-Supervised Learningcited by 1
  8. 2024Weights Augmentation: it has never ever ever ever let her model downcited by 1
  9. 2022SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpuscited by 0
  10. 2023Online Non-Destructive Moisture Content Estimation of Filter Media During Drying Using Artificial Neural Networkscited by 0
  11. 2023ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden Statescited by 0
  12. 2023ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averagingcited by 0
  13. 2025Relevance-driven Input Dropout: an Explanation-guided Regularization Techniquecited by 0
  14. 2025A Neural Network-Based Real-time Casing Collar Recognition System for Downhole Instrumentscited by 0
  15. 2026Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussioncited by 0