mlsanityData to 7 Oct 2026

Shake-Shake regularization

arXiv 1705.07485 ↗First posted 21 May 2017cs.LG cs.CVcited by 87

Not on the map. Why?

Abstract (arXiv)

The method introduced in this paper aims at helping deep learning practitioners faced with an overfit problem. The idea is to replace, in a multi-branch network, the standard summation of parallel branches with a stochastic affine combination. Applied to 3-branch residual networks, shake-shake regularization improves on the best single shot published results on CIFAR-10 and CIFAR-100 by reaching test errors of 2.86% and 15.85%. Experiments on architectures without skip connections or Batch Normalization show encouraging results and open the door to a large set of applications. Code is available at https://github.com/xgastaldi/shake-shake

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 17; 2023: 13; 2024: 14; 2025: 4; 2026: 4.

87 papers.

Sort:

By area:

  1. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  2. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 254
  3. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
  4. 2022Surrogate Gap Minimization Improves Sharpness-Aware Trainingcited by 171
  5. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  6. 2021On Training Implicit Modelscited by 73
  7. 2021Meta Gradient Adversarial Attackcited by 55
  8. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  9. 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
  10. 2022TeachAugment: Data Augmentation Optimization Using Teacher Knowledgecited by 37
  11. 2021Spectral Bias in Practice: The Role of Function Frequency in Generalizationcited by 36
  12. 2021Direct Differentiable Augmentation Searchcited by 28
38 more
  1. 2021Efficient Certified Defenses Against Patch Attacks on Image Classifierscited by 23
  2. 2021Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimizationcited by 19
  3. 2022Bootstrap Generalization Ability from Loss Landscape Perspectivecited by 16
  4. 2023Pathologies of Predictive Diversity in Deep Ensemblescited by 16
  5. 2021DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximizationcited by 15
  6. 2021Evaluating State-of-the-Art Classification Models Against Bayes Optimalitycited by 15
  7. 2021Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentationcited by 13
  8. 2022Improving Robustness with Adaptive Weight Decaycited by 13
  9. 2023When to Learn What: Model-Adaptive Data Augmentation Curriculumcited by 13
  10. 2024EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classificationcited by 13
  11. 2021One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinkingcited by 12
  12. 2022On the Informativeness of Supervision Signalscited by 12
  13. 2025Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splattingcited by 12
  14. 2021SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentationcited by 10
  15. 2022On the Origins of the Block Structure Phenomenon in Neural Network Representationscited by 10
  16. 2024Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Surveycited by 10
  17. 2022Exploring Temporally Dynamic Data Augmentation for Video Recognitioncited by 9
  18. 2024DiffsFormer: A Diffusion Transformer on Stock Factor Augmentationcited by 9
  19. 2021Local Patch AutoAugment with Multi-Agent Collaborationcited by 8
  20. 2021Escaping Saddle Points Faster with Stochastic Momentumcited by 8
  21. 2023Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarizationcited by 8
  22. 2021BasisNet: Two-stage Model Synthesis for Efficient Inferencecited by 7
  23. 2022AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classificationcited by 7
  24. 2024AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentationcited by 7
  25. 2021An Empirical Study and Analysis on Open-Set Semi-Supervised Learningcited by 6
  26. 2021Synthetic Data for Model Selectioncited by 6
  27. 2021Adaptive Perturbation for Adversarial Attackcited by 6
  28. 2023Inconsistency, Instability, and Generalization Gap of Deep Neural Network Trainingcited by 6
  29. 2021Diffusion Mechanism in Residual Neural Network: Theory and Applicationscited by 5
  30. 2021Improving Model Generalization by Agreement of Learned Representations from Data Augmentationcited by 5
  31. 2022Universal Adaptive Data Augmentationcited by 5
  32. 2025Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognitioncited by 5
  33. 2021Bag of Tricks for Neural Architecture Searchcited by 4
  34. 2021Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groupscited by 4
  35. 2022A Survey on Dropout Methods and Experimental Verification in Recommendationcited by 4
  36. 2022Estimating Structural Disparities for Face Modelscited by 4
  37. 2023Sparse then Prune: Toward Efficient Vision Transformerscited by 4
  38. 2021Improving Classification Accuracy with Graph Filteringcited by 3

50 most cited of 87 All 87 (JSON)