mlsanityData to 14 Oct 2026

TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation

arXiv 2103.10158 ↗First posted 18 Mar 2021cs.CV cs.LGcited by 227

Not on the map. Why?

Abstract (arXiv)

Automatic augmentation methods have recently become a crucial pillar for strong model performance in vision tasks. While existing automatic augmentation methods need to trade off simplicity, cost and performance, we present a most simple baseline, TrivialAugment, that outperforms previous methods for almost free. TrivialAugment is parameter-free and only applies a single augmentation to each image. Thus, TrivialAugment's effectiveness is very unexpected to us and we performed very thorough experiments to study its performance. First, we compare TrivialAugment to previous state-of-the-art methods in a variety of image classification scenarios. Then, we perform multiple ablation studies with different augmentation spaces, augmentation methods and setups to understand the crucial requirements for its performance. Additionally, we provide a simple interface to facilitate the widespread adoption of automatic augmentation methods, as well as our full code base for reproducibility. Since our work reveals a stagnation in many parts of automatic augmentation research, we end with a short proposal of best practices for sustained future progress in automatic augmentation methods.

Key facts. Cited by 227 papers in the map (data through 14 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 18 Mar 2021.

Builds on

17 of 23 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2016Wide Residual Networkscited by 3,070
  5. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  7. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  8. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  9. 2019Fast AutoAugmentcited by 243
  10. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 154
  11. 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
  12. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
5 more
  1. 2019Adversarial AutoAugmentcited by 111
  2. 2017Shake-Shake regularizationcited by 87
  3. 2019Online Hyper-parameter Learning for Auto-Augmentation Strategycited by 38
  4. 2020UniformAugment: A Search-free Probabilistic Data Augmentation Approachcited by 38
  5. 2020Improving Auto-Augment via Augmentation-Wise Weight Sharingcited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 27; 2023: 55; 2024: 64; 2025: 43; 2026: 32.

227 papers.

Sort:

By area:

  1. 2022DeiT III: Revenge of the ViTcited by 419
  2. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  3. 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 147
  4. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  5. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  6. 2023Class Attention Transfer Based Knowledge Distillationcited by 61
  7. 2023Data Augmentation Alone Can Improve Adversarial Trainingcited by 43
  8. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
  9. 2022How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularizationcited by 40
  10. 2023SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentationcited by 39
  11. 2023An Empirical Study of CLIP for Text-based Person Searchcited by 38
  12. 2022TeachAugment: Data Augmentation Optimization Using Teacher Knowledgecited by 37
38 more
  1. 2023AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challengecited by 35
  2. 2023B-cos Alignment for Inherently Interpretable CNNs and Vision Transformerscited by 31
  3. 2022Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentationcited by 30
  4. 2023Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attackscited by 30
  5. 2024AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Modelscited by 30
  6. 2023DiffBoost: Enhancing Medical Image Segmentation via Text-Guided Diffusion Modelcited by 23
  7. 2025Position: The Future of Bayesian Prediction Is Prior-Fittedcited by 20
  8. 2022WaveMix: A Resource-efficient Neural Network for Image Analysiscited by 19
  9. 2022Deep AutoAugmentcited by 18
  10. 2022Learning Multimodal Data Augmentation in Feature Spacecited by 18
  11. 2023Simplifying Neural Network Training Under Class Imbalancecited by 18
  12. 2024Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classificationcited by 18
  13. 2022Automatic Data Augmentation via Invariance-Constrained Learningcited by 17
  14. 2024Evolve Cost-aware Acquisition Functions Using Large Language Modelscited by 17
  15. 2022On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learningcited by 16
  16. 2024Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesiscited by 16
  17. 2023PED-ANOVA: Efficiently Quantifying Hyperparameter Importance in Arbitrary Subspacescited by 15
  18. 2023Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentationcited by 14
  19. 2023IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifierscited by 14
  20. 2024Automated data processing and feature engineering for deep learning and big data applications: a surveycited by 14
  21. 2024Twins-PainViT: Towards a Modality-Agnostic Vision Transformer Framework for Multimodal Automatic Pain Assessment using Facial Videos and fNIRScited by 14
  22. 2025OpenMIBOOD: Open Medical Imaging Benchmarks for Out-Of-Distribution Detectioncited by 14
  23. 2021Learning Augmentation Distributions using Transformed Risk Minimizationcited by 13
  24. 2022Improving Robustness with Adaptive Weight Decaycited by 13
  25. 2023When to Learn What: Model-Adaptive Data Augmentation Curriculumcited by 13
  26. 2023Understanding the Detrimental Class-level Effects of Data Augmentationcited by 13
  27. 2024Revisiting Adversarial Training under Long-Tailed Distributionscited by 13
  28. 2024Frozen Feature Augmentation for Few-Shot Image Classificationcited by 13
  29. 2024EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classificationcited by 13
  30. 2023Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritagecited by 12
  31. 2023BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mappingcited by 12
  32. 2022Soft Augmentation for Image Classificationcited by 11
  33. 2023Interpreting and Correcting Medical Image Classification with PIP-Netcited by 11
  34. 2022Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classificationcited by 10
  35. 2023Improving Adversarial Transferability via Model Alignmentcited by 10
  36. 2024MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)cited by 10
  37. 2025PainFormer: a Vision Foundation Model for Automatic Pain Assessmentcited by 10
  38. 2022Exploring Temporally Dynamic Data Augmentation for Video Recognitioncited by 9

50 most cited of 227 All 227 (JSON)