# DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data

arXiv: https://arxiv.org/abs/2105.02340 · HTML: https://mlsanity.com/paper/2105.02340/

## 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 (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [Are GANs Created Equal? A Large-Scale Study](https://mlsanity.com/paper/1711.10337/) (2017)
- [Generative Adversarial Network in Medical Imaging: A Review](https://mlsanity.com/paper/1809.07294/) (2018)
- [Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data](https://mlsanity.com/paper/1508.03422/) (2015)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [Range Loss for Deep Face Recognition with Long-tail](https://mlsanity.com/paper/1611.08976/) (2016)
- [Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis](https://mlsanity.com/paper/1606.04316/) (2016)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [BAGAN: Data Augmentation with Balancing GAN](https://mlsanity.com/paper/1803.09655/) (2018)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Imbalanced Deep Learning by Minority Class Incremental Rectification](https://mlsanity.com/paper/1804.10851/) (2018)
- [Deep Over-sampling Framework for Classifying Imbalanced Data](https://mlsanity.com/paper/1704.07515/) (2017)

## Built on by (most cited first, 30 of 64)

- [Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learning](https://mlsanity.com/paper/2207.06084/) (2022)
- [Feature Generation for Long-tail Classification](https://mlsanity.com/paper/2111.05956/) (2021)
- [Efficient Augmentation for Imbalanced Deep Learning](https://mlsanity.com/paper/2207.06080/) (2022)
- [Effective Class-Imbalance learning based on SMOTE and Convolutional Neural Networks](https://mlsanity.com/paper/2209.00653/) (2022)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese](https://mlsanity.com/paper/2402.07513/) (2024)
- [Tailoring Mixup to Data for Calibration](https://mlsanity.com/paper/2311.01434/) (2023)
- [ChildGAN: Large Scale Synthetic Child Facial Data Using Domain Adaptation in StyleGAN](https://mlsanity.com/paper/2307.13746/) (2023)
- [IB-GAN: A Unified Approach for Multivariate Time Series Classification under Class Imbalance](https://mlsanity.com/paper/2110.07460/) (2021)
- [Advancing DDoS Attack Detection: A Synergistic Approach Using Deep Residual Neural Networks and Synthetic Oversampling](https://mlsanity.com/paper/2401.03116/) (2024)
- [Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling](https://mlsanity.com/paper/2501.04666/) (2025)
- [Deep Learning Meets Oversampling: A Learning Framework to Handle Imbalanced Classification](https://mlsanity.com/paper/2502.06878/) (2025)
- [SMOTExT: SMOTE meets Large Language Models](https://mlsanity.com/paper/2505.13434/) (2025)
- [Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models](https://mlsanity.com/paper/2507.13874/) (2025)
- [On the combined effect of class imbalance and concept complexity in deep learning](https://mlsanity.com/paper/2107.14194/) (2021)
- [Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation](https://mlsanity.com/paper/2203.00452/) (2022)
- [A Distributed Approach to Meteorological Predictions: Addressing Data Imbalance in Precipitation Prediction Models through Federated Learning and GANs](https://mlsanity.com/paper/2310.13161/) (2023)
- [Machine Learning Approaches for Diagnostics and Prognostics of Industrial Systems Using Open Source Data from PHM Data Challenges: A Review](https://mlsanity.com/paper/2312.16810/) (2023)
- [AEMLO: AutoEncoder-Guided Multi-Label Oversampling](https://mlsanity.com/paper/2408.13078/) (2024)
- [A Hybrid Approach for Binary Classification of Imbalanced Data](https://mlsanity.com/paper/2207.02738/) (2022)
- [Towards Understanding How Data Augmentation Works with Imbalanced Data](https://mlsanity.com/paper/2304.05895/) (2023)
- [From SMOTE to Mixup for Deep Imbalanced Classification](https://mlsanity.com/paper/2308.15457/) (2023)
- [MCRAGE: Synthetic Healthcare Data for Fairness](https://mlsanity.com/paper/2310.18430/) (2023)
- [Deep Similarity Learning Loss Functions in Data Transformation for Class Imbalance](https://mlsanity.com/paper/2312.10556/) (2023)
- [Synthetic Information towards Maximum Posterior Ratio for deep learning on Imbalanced Data](https://mlsanity.com/paper/2401.02591/) (2024)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)
- [Improving SMOTE via Fusing Conditional VAE for Data-adaptive Noise Filtering](https://mlsanity.com/paper/2405.19757/) (2024)
- [Privacy-Preserved Taxi Demand Prediction System Utilizing Distributed Data](https://mlsanity.com/paper/2408.04931/) (2024)
- [Text-Guided Mixup Towards Long-Tailed Image Categorization](https://mlsanity.com/paper/2409.03583/) (2024)
- [Local Lesion Generation is Effective for Capsule Endoscopy Image Data Augmentation in a Limited Data Setting](https://mlsanity.com/paper/2411.03098/) (2024)

## 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