mlsanityData to 7 Oct 2026

TeachAugment: Data Augmentation Optimization Using Teacher Knowledge

arXiv 2202.12513 ↗First posted 25 Feb 2022cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Optimization of image transformation functions for the purpose of data augmentation has been intensively studied. In particular, adversarial data augmentation strategies, which search augmentation maximizing task loss, show significant improvement in the model generalization for many tasks. However, the existing methods require careful parameter tuning to avoid excessively strong deformations that take away image features critical for acquiring generalization. In this paper, we propose a data augmentation optimization method based on the adversarial strategy called TeachAugment, which can produce informative transformed images to the model without requiring careful tuning by leveraging a teacher model. Specifically, the augmentation is searched so that augmented images are adversarial for the target model and recognizable for the teacher model. We also propose data augmentation using neural networks, which simplifies the search space design and allows for updating of the data augmentation using the gradient method. We show that TeachAugment outperforms existing methods in experiments of image classification, semantic segmentation, and unsupervised representation learning tasks.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 49 of its 66 references that are in the map. First posted on arXiv 25 Feb 2022.

Builds on

49 of 66 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  9. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  10. 2016Wide Residual Networkscited by 3,057
  11. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  12. 2020Exploring Simple Siamese Representation Learningcited by 2,853
37 more
  1. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  2. 2016Pyramid Scene Parsing Networkcited by 2,472
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2015Spatial Transformer Networkscited by 1,423
  10. 2017Random Erasing Data Augmentationcited by 1,235
  11. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  12. 2015Prioritized Experience Replaycited by 1,070
  13. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  14. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  15. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  16. 2019Fast AutoAugmentcited by 243
  17. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
  18. 2016Deep Pyramidal Residual Networkscited by 163
  19. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  20. 2019Adversarial AutoAugmentcited by 111
  21. 2018Data Augmentation by Pairing Samples for Images Classificationcited by 96
  22. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  23. 2017Shake-Shake regularizationcited by 87
  24. 2020PointAugment: an Auto-Augmentation Framework for Point Cloud Classificationcited by 65
  25. 2020DADA: Differentiable Automatic Data Augmentationcited by 57
  26. 2017Between-class Learning for Image Classificationcited by 50
  27. 2016Connecting Generative Adversarial Networks and Actor-Critic Methodscited by 49
  28. 2018Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimationcited by 44
  29. 2018ShakeDrop Regularization for Deep Residual Learningcited by 40
  30. 2019Online Hyper-parameter Learning for Auto-Augmentation Strategycited by 38
  31. 2020UniformAugment: A Search-free Probabilistic Data Augmentation Approachcited by 38
  32. 2020SelfAugment: Automatic Augmentation Policies for Self-Supervised Learningcited by 32
  33. 2020Circumventing Outliers of AutoAugment with Knowledge Distillationcited by 29
  34. 2020OnlineAugment: Online Data Augmentation with Less Domain Knowledgecited by 28
  35. 2020Improving Auto-Augment via Augmentation-Wise Weight Sharingcited by 28
  36. 2020Meta Approach to Data Augmentation Optimizationcited by 22
  37. 2019Adversarial Transformations for Semi-Supervised Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 10; 2024: 11; 2025: 7; 2026: 2.

37 papers.

Sort:

  1. 2024Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classificationcited by 18
  2. 2022Learning Multimodal Data Augmentation in Feature Spacecited by 17
  3. 2023When to Learn What: Model-Adaptive Data Augmentation Curriculumcited by 13
  4. 2024EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classificationcited by 13
  5. 2024SUMix: Mixup with Semantic and Uncertain Informationcited by 12
  6. 2023Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learningcited by 8
  7. 2022Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentationcited by 7
  8. 2024AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentationcited by 7
  9. 2023SLACK: Stable Learning of Augmentations with Cold-start and KL regularizationcited by 6
  10. 2022Deeper Insights into the Robustness of ViTs towards Common Corruptionscited by 5
  11. 2022Teaching What You Should Teach: A Data-Based Distillation Methodcited by 5
  12. 2023Domain Generalization by Rejecting Extreme Augmentationscited by 5
25 more
  1. 2025Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clientscited by 5
  2. 2025Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognitioncited by 5
  3. 2022ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentationcited by 3
  4. 2023Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOIcited by 3
  5. 2024FreeAugment: Data Augmentation Search Across All Degrees of Freedomcited by 3
  6. 2024Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentationcited by 3
  7. 2025SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selectioncited by 3
  8. 2024Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learningcited by 2
  9. 2024Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operationscited by 2
  10. 2022Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformerscited by 1
  11. 2023Clothes Grasping and Unfolding Based on RGB-D Semantic Segmentationcited by 1
  12. 2023Target-driven One-Shot Unsupervised Domain Adaptationcited by 1
  13. 2023Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptationcited by 1
  14. 2023DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejectioncited by 1
  15. 2024Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methodscited by 1
  16. 2024Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identificationcited by 1
  17. 2024CAAP: Class-Dependent Automatic Data Augmentation Based On Adaptive Policies For Time Seriescited by 1
  18. 2025Enhancing Small-Scale Dataset Expansion with Triplet-Connection-based Sample Re-Weightingcited by 1
  19. 2025On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimationcited by 1
  20. 2022Local Magnification for Data and Feature Augmentationcited by 0
  21. 2023Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Studycited by 0
  22. 2025Self-Supervised Learning for Neural Topic Models with Variance-Invariance-Covariance Regularizationcited by 0
  23. 2025Data-Augmented Quantization-Aware Knowledge Distillationcited by 0
  24. 2026AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognitioncited by 0
  25. 2026Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasetscited by 0