mlsanityData to 14 Oct 2026

DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data

arXiv 2105.02340 ↗First posted 5 May 2021cs.CV cs.LGcited by 64

Not on the map. Why?

Abstract (arXiv)

Despite over two decades of progress, imbalanced data is still considered a significant challenge for contemporary machine learning models. Modern advances in deep learning have magnified the importance of the imbalanced data problem. The two main approaches to address this issue are based on loss function modifications and instance resampling. Instance sampling is typically based on Generative Adversarial Networks (GANs), which may suffer from mode collapse. Therefore, there is a need for an oversampling method that is specifically tailored to deep learning models, can work on raw images while preserving their properties, and is capable of generating high quality, artificial images that can enhance minority classes and balance the training set. We propose DeepSMOTE - a novel oversampling algorithm for deep learning models. It is simple, yet effective in its design. It consists of three major components: (i) an encoder/decoder framework; (ii) SMOTE-based oversampling; and (iii) a dedicated loss function that is enhanced with a penalty term. An important advantage of DeepSMOTE over GAN-based oversampling is that DeepSMOTE does not require a discriminator, and it generates high-quality artificial images that are both information-rich and suitable for visual inspection. DeepSMOTE code is publicly available at: https://github.com/dd1github/DeepSMOTE

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Builds on 43 of its 119 references that are in the map. First posted on arXiv 5 May 2021.

Builds on

43 of 119 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  8. 2016Improved Techniques for Training GANscited by 2,970
  9. 2017Improved Training of Wasserstein GANscited by 2,235
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  12. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
31 more
  1. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  2. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  3. 2016Tutorial on Variational Autoencoderscited by 409
  4. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  5. 2017Wasserstein Auto-Encoderscited by 373
  6. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  7. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 274
  8. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  9. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  10. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  11. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  12. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111
  13. 2016Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysiscited by 93
  14. 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 91
  15. 2018BAGAN: Data Augmentation with Balancing GANcited by 90
  16. 2019Generative Adversarial Minority Oversamplingcited by 73
  17. 2018Imbalanced Deep Learning by Minority Class Incremental Rectificationcited by 65
  18. 2017Deep Over-sampling Framework for Classifying Imbalanced Datacited by 59
  19. 2016Connecting Generative Adversarial Networks and Actor-Critic Methodscited by 50
  20. 2019LOGAN: Latent Optimisation for Generative Adversarial Networkscited by 42
  21. 2019Radial-Based Undersampling for Imbalanced Data Classificationcited by 22
  22. 2019Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representationscited by 19
  23. 2020Combined Cleaning and Resampling Algorithm for Multi-Class Imbalanced Data with Label Noisecited by 18
  24. 2021Class-Incremental Experience Replay for Continual Learning under Concept Driftcited by 17
  25. 2017On Unifying Deep Generative Modelscited by 15
  26. 2021Concept Drift Detection from Multi-Class Imbalanced Data Streamscited by 13
  27. 2018A Cost-Sensitive Deep Belief Network for Imbalanced Classificationcited by 12
  28. 2020Long-Tailed Recognition Using Class-Balanced Expertscited by 10
  29. 2020ReMix: Calibrated Resampling for Class Imbalance in Deep learningcited by 10
  30. 2017Boosting with Lexicographic Programming: Addressing Class Imbalance without Cost Tuningcited by 3
  31. 2019Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Trainingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 13; 2024: 11; 2025: 18; 2026: 10.

64 papers.

Sort:

By area:

  1. 2022Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learningcited by 10
  2. 2021Feature Generation for Long-tail Classificationcited by 9
  3. 2022Efficient Augmentation for Imbalanced Deep Learningcited by 6
  4. 2022Effective Class-Imbalance learning based on SMOTE and Convolutional Neural Networkscited by 6
  5. 2023Data Optimization in Deep Learning: A Surveycited by 6
  6. 2024The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguesecited by 6
  7. 2023Tailoring Mixup to Data for Calibrationcited by 5
  8. 2023ChildGAN: Large Scale Synthetic Child Facial Data Using Domain Adaptation in StyleGANcited by 4
  9. 2021IB-GAN: A Unified Approach for Multivariate Time Series Classification under Class Imbalancecited by 3
  10. 2024Advancing DDoS Attack Detection: A Synergistic Approach Using Deep Residual Neural Networks and Synthetic Oversamplingcited by 3
  11. 2025Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Schedulingcited by 3
  12. 2025Deep Learning Meets Oversampling: A Learning Framework to Handle Imbalanced Classificationcited by 3
38 more
  1. 2025SMOTExT: SMOTE meets Large Language Modelscited by 3
  2. 2025Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Modelscited by 3
  3. 2021On the combined effect of class imbalance and concept complexity in deep learningcited by 2
  4. 2022Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generationcited by 2
  5. 2023A Distributed Approach to Meteorological Predictions: Addressing Data Imbalance in Precipitation Prediction Models through Federated Learning and GANscited by 2
  6. 2023Machine Learning Approaches for Diagnostics and Prognostics of Industrial Systems Using Open Source Data from PHM Data Challenges: A Reviewcited by 2
  7. 2024AEMLO: AutoEncoder-Guided Multi-Label Oversamplingcited by 2
  8. 2022A Hybrid Approach for Binary Classification of Imbalanced Datacited by 1
  9. 2023Towards Understanding How Data Augmentation Works with Imbalanced Datacited by 1
  10. 2023From SMOTE to Mixup for Deep Imbalanced Classificationcited by 1
  11. 2023MCRAGE: Synthetic Healthcare Data for Fairnesscited by 1
  12. 2023Deep Similarity Learning Loss Functions in Data Transformation for Class Imbalancecited by 1
  13. 2024Synthetic Information towards Maximum Posterior Ratio for deep learning on Imbalanced Datacited by 1
  14. 2024Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methodscited by 1
  15. 2024Improving SMOTE via Fusing Conditional VAE for Data-adaptive Noise Filteringcited by 1
  16. 2024Privacy-Preserved Taxi Demand Prediction System Utilizing Distributed Datacited by 1
  17. 2024Text-Guided Mixup Towards Long-Tailed Image Categorizationcited by 1
  18. 2024Local Lesion Generation is Effective for Capsule Endoscopy Image Data Augmentation in a Limited Data Settingcited by 1
  19. 2025Does Prior Data Matter? Exploring Joint Training in the Context of Few-Shot Class-Incremental Learningcited by 1
  20. 2025A Survey on Small Sample Imbalance Problem: Metrics, Feature Analysis, and Solutionscited by 1
  21. 2025VR-FuseNet: A Fusion of Heterogeneous Fundus Data and Explainable Deep Network for Diabetic Retinopathy Classificationcited by 1
  22. 2025Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methodscited by 1
  23. 2022A Light in the Dark: Deep Learning Practices for Industrial Computer Visioncited by 0
  24. 2022Predicting Terrorist Attacks in the United States using Localized News Datacited by 0
  25. 2022Imbalanced Classification via Explicit Gradient Learning From Augmented Datacited by 0
  26. 2022Interpretable ML for Imbalanced Datacited by 0
  27. 2023Neural Network Architecture for Database Augmentation Using Shared Featurescited by 0
  28. 2023Astronomical image time series classification using CONVolutional attENTION (ConvEntion)cited by 0
  29. 2023INGB: Informed Nonlinear Granular Ball Oversampling Framework for Noisy Imbalanced Classificationcited by 0
  30. 2023Fair GANs through model rebalancing for extremely imbalanced class distributionscited by 0
  31. 2024Class-Aware Contrastive Optimization for Imbalanced Text Classificationcited by 0
  32. 2024Federated Unlearning Model Recovery in Data with Skewed Label Distributionscited by 0
  33. 2025Deep Minimax Classifiers for Imbalanced Datasets with a Small Number of Minority Samplescited by 0
  34. 2025A Novel Double Pruning method for Imbalanced Data using Information Entropy and Roulette Wheel Selection for Breast Cancer Diagnosiscited by 0
  35. 2025Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resamplingcited by 0
  36. 2025Deep Learning Methods for Detecting Thermal Runaway Events in Battery Production Linescited by 0
  37. 2025Approximate Borderline Sampling using Granular-Ball for Classification Taskscited by 0
  38. 2025Taming Data Challenges in ML-based Security Tasks Using Generative AIcited by 0

50 most cited of 64 All 64 (JSON)