2023/12/05 by Ravid Shwartz-Ziv, Shwartz-Ziv, Ravid, Micah Goldblum +7 · 1 voice · 2 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Electricity Theft Detection Techniques #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Vehicle License Plate Recognition #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2312.02517
openalex publication_date 2023/12/05 · arxiv published 2023/12/05 · arxiv updated 2023/12/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques, or two-stage training procedures. Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, optimizer, and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods. We also provide key prescriptions and considerations for training under class imbalance, and an understanding of why imbalance methods succeed or fail.