DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data

2021/05/05 by Damien Dablain, Dablain, Damien, Bartosz Krawczyk +3 · 8 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Image and Object Detection Techniques #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2105.02340

openalex publication_date 2021/05/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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

Cited by

• Deep Imbalanced Multi-Target Regression: 3D Point Cloud Voxel Content Estimation in Simulated Forests
• EASELAN: An Open-Source Framework for Multimodal Biosignal Annotation and Data Management
• AxelSMOTE: An Agent-Based Oversampling Algorithm for Imbalanced Classification
• Enhancing Machine Learning for Imbalanced Medical Data: A Quantum-Inspired Approach to Synthetic Oversampling (QI-SMOTE)
• Harmonized Gradient Descent for Class Imbalanced Data Stream Online Learning
• Towards Balanced Behavior Cloning from Imbalanced Datasets
• Large Language Models as Innovators: A Framework to Leverage Latent Space Exploration for Novelty Discovery
• Taming Data Challenges in ML-based Security Tasks Using Generative AI

Related

• Deep Learning Meets Oversampling: A Learning Framework to Handle Imbalanced Classification
• Efficient Augmentation for Imbalanced Deep Learning
• From SMOTE to Mixup for Deep Imbalanced Classification
• ReMix: Calibrated Resampling for Class Imbalance in Deep learning
• Minority Class Oversampling for Tabular Data with Deep Generative Models