# Discriminative feature generation for classification of imbalanced data

arXiv: https://arxiv.org/abs/2010.12888 · HTML: https://mlsanity.com/paper/2010.12888/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation](https://mlsanity.com/paper/2303.07012/) (2023)
- [DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.02173/) (2022)
- [Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning](https://mlsanity.com/paper/2112.07015/) (2021)
- [Generalization Gap in Data Augmentation: Insights from Illumination](https://mlsanity.com/paper/2404.07514/) (2024)
- [Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks](https://mlsanity.com/paper/2109.12513/) (2021)
- [ODMTCNet: An Interpretable Multi-view Deep Neural Network Architecture for Image Feature Representation](https://mlsanity.com/paper/2110.14830/) (2021)
- [Introducing the O-Value: A Universal Standardization for Confusion-Matrix-Based Classification Performance Metrics](https://mlsanity.com/paper/2505.07033/) (2025)

## Abstract (arXiv)

The data imbalance problem is a frequent bottleneck in the classification performance of neural networks. In this paper, we propose a novel supervised discriminative feature generation (DFG) method for a minority class dataset. DFG is based on the modified structure of a generative adversarial network consisting of four independent networks: generator, discriminator, feature extractor, and classifier. To augment the selected discriminative features of the minority class data by adopting an attention mechanism, the generator for the class-imbalanced target task is trained, and the feature extractor and classifier are regularized using the pre-trained features from a large source data. The experimental results show that the DFG generator enhances the augmentation of the label-preserved and diverse features, and the classification results are significantly improved on the target task. The feature generation model can contribute greatly to the development of data augmentation methods through discriminative feature generation and supervised attention methods.