mlsanityData to 14 Oct 2026

An overview of mixing augmentation methods and augmentation strategies

arXiv 2107.09887 ↗First posted 21 Jul 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017-2021.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 60 of its 91 references that are in the map. First posted on arXiv 21 Jul 2021.

Builds on

60 of 91 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2017Proximal Policy Optimization Algorithmscited by 15,215
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2016Wide Residual Networkscited by 3,070
  11. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  12. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
38 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,659
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  6. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  9. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  11. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  12. 2017Random Erasing Data Augmentationcited by 1,239
  13. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  14. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  15. 2021Domain Generalization with MixStylecited by 566
  16. 2017Population Based Training of Neural Networkscited by 367
  17. 2018DropBlock: A regularization method for convolutional networkscited by 262
  18. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 261
  19. 2019Fast AutoAugmentcited by 243
  20. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 232
  21. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  22. 2016Deep Pyramidal Residual Networkscited by 163
  23. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  24. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 154
  25. 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
  26. 2015A Large-Scale Car Dataset for Fine-Grained Categorization and Verificationcited by 130
  27. 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 128
  28. 2017Dataset Augmentation in Feature Spacecited by 124
  29. 2019Adversarial AutoAugmentcited by 111
  30. 2021Fair Mixup: Fairness via Interpolationcited by 109
  31. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  32. 2017Backpropagation through the Void: Optimizing control variates for black-box gradient estimationcited by 106
  33. 2019Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentationcited by 105
  34. 2018Data Augmentation by Pairing Samples for Images Classificationcited by 96
  35. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  36. 2017Regularization for Deep Learning: A Taxonomycited by 91
  37. 2017Exploring the structure of a real-time, arbitrary neural artistic stylization networkcited by 89
  38. 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 1; 2025: 3; 2026: 1.

14 papers.

Sort:

  1. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 31
  2. 2022OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learningcited by 21
  3. 2024A Survey on Mixup Augmentations and Beyondcited by 20
  4. 2022GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clusteringcited by 13
  5. 2022StatMix: Data augmentation method that relies on image statistics in federated learningcited by 4
  6. 2023Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesicscited by 3
  7. 2025Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentationcited by 3
  8. 2023AttentionMix: Data augmentation method that relies on BERT attention mechanismcited by 2
  9. 2022A General Multiple Data Augmentation Based Framework for Training Deep Neural Networkscited by 0
  10. 2023Neural Network Architecture for Database Augmentation Using Shared Featurescited by 0
  11. 2023Enhancing Visual Perception in Novel Environments via Incremental Data Augmentation Based on Style Transfercited by 0
  12. 2025Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentationcited by 0
2 more
  1. 2025Synthetic Data Augmentation for Enhanced Chicken Carcass Instance Segmentationcited by 0
  2. 2026Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentationcited by 0