mlsanityData to 14 Oct 2026

Improving Deep Learning using Generic Data Augmentation

arXiv 1708.06020 ↗First posted 20 Aug 2017cs.LG stat.MLcited by 36

Not on the map. Why?

Abstract (arXiv)

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating the training set with label preserving transformations. Recently there has been extensive use of generic data augmentation to improve Convolutional Neural Network (CNN) task performance. This study benchmarks various popular data augmentation schemes to allow researchers to make informed decisions as to which training methods are most appropriate for their data sets. Various geometric and photometric schemes are evaluated on a coarse-grained data set using a relatively simple CNN. Experimental results, run using 4-fold cross-validation and reported in terms of Top-1 and Top-5 accuracy, indicate that cropping in geometric augmentation significantly increases CNN task performance.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 14; 2022: 15; 2023: 5; 2024: 2.

36 papers.

Sort:

By area:

  1. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  2. 2022How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularizationcited by 40
  3. 2021BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtractioncited by 15
  4. 2021Improved YOLOv5 network for real-time multi-scale traffic sign detectioncited by 11
  5. 2022Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solverscited by 9
  6. 2024RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Modelscited by 8
  7. 2021Sill-Net: Feature Augmentation with Separated Illumination Representationcited by 7
  8. 2022Invariance encoding in sliced-Wasserstein space for image classification with limited training datacited by 7
  9. 2022DiffML: End-to-end Differentiable ML Pipelinescited by 7
  10. 2022Apple Counting using Convolutional Neural Networkscited by 7
  11. 2021Image Captioning using Deep Stacked LSTMs, Contextual Word Embeddings and Data Augmentationcited by 5
  12. 2021Principled Ultrasound Data Augmentation for Classification of Standard Planescited by 5
24 more
  1. 2021Fast Jacobian-Vector Product for Deep Networkscited by 4
  2. 2021Landmarks Augmentation with Manifold-Barycentric Oversamplingcited by 4
  3. 2021Controllable Data Augmentation Through Deep Relightingcited by 4
  4. 2022PIAT: Physics Informed Adversarial Training for Solving Partial Differential Equationscited by 4
  5. 2022Agile Effort Estimation: Have We Solved the Problem Yet? Insights From A Replication Studycited by 3
  6. 2022Feature transforms for image data augmentationcited by 3
  7. 2022Image Augmentation for Satellite Imagescited by 3
  8. 2023An Improved Data Augmentation Scheme for Model Predictive Control Policy Approximationcited by 3
  9. 2024How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?cited by 3
  10. 2021Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approachcited by 2
  11. 2022Iterative training of robust k-space interpolation networks for improved image reconstruction with limited scan specific training samplescited by 2
  12. 2022Video2IMU: Realistic IMU features and signals from videoscited by 1
  13. 2022Application of multilayer perceptron with data augmentation in nuclear physicscited by 1
  14. 2022The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneckcited by 1
  15. 2023Embarrassingly Simple MixUp for Time-seriescited by 1
  16. 2021Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNNcited by 0
  17. 2021Explainability Guided Multi-Site COVID-19 CT Classificationcited by 0
  18. 2021Deep learning facilitates fully automated brain image registration of optoacoustic tomography and magnetic resonance imagingcited by 0
  19. 2021Generatively Augmented Neural Network Watchdog for Image Classification Networkscited by 0
  20. 2022Ensemble Learning techniques for object detection in high-resolution satellite imagescited by 0
  21. 2022Improving Sample Efficiency of Deep Learning Models in Electricity Marketcited by 0
  22. 2023Efficient Training Under Limited Resourcescited by 0
  23. 2023Fine-Grained ImageNet Classification in the Wildcited by 0
  24. 2023Simple Noisy Environment Augmentation for Reinforcement Learningcited by 0