# Distribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification

arXiv: https://arxiv.org/abs/2207.12744 · HTML: https://mlsanity.com/paper/2207.12744/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 26 Jul 2022.

## Builds on (most cited first, 9 of 9)

- [Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network](https://mlsanity.com/paper/1805.00728/) (2018)
- [Molecular generative model based on conditional variational autoencoder for de novo molecular design](https://mlsanity.com/paper/1806.05805/) (2018)
- [Jointly Measuring Diversity and Quality in Text Generation Models](https://mlsanity.com/paper/1904.03971/) (2019)
- [Data-Efficient Instance Generation from Instance Discrimination](https://mlsanity.com/paper/2106.04566/) (2021)
- [Rethinking Feature Distribution for Loss Functions in Image Classification](https://mlsanity.com/paper/1803.02988/) (2018)
- [Exploring the Evolution of GANs through Quality Diversity](https://mlsanity.com/paper/2007.06251/) (2020)
- [On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation](https://mlsanity.com/paper/2007.01488/) (2020)
- [Handling Imbalanced Classification Problems With Support Vector Machines via Evolutionary Bilevel Optimization](https://mlsanity.com/paper/2204.10231/) (2022)
- [Enhancing Gaussian Estimation of Distribution Algorithm by Exploiting Evolution Direction with Archive](https://mlsanity.com/paper/1802.08989/) (2018)

## Abstract (arXiv)

To address the trade-off problem of quality-diversity for the generated images in imbalanced classification tasks, we research on over-sampling based methods at the feature level instead of the data level and focus on searching the latent feature space for optimal distributions. On this basis, we propose an iMproved Estimation Distribution Algorithm based Latent featUre Distribution Evolution (MEDA_LUDE) algorithm, where a joint learning procedure is programmed to make the latent features both optimized and evolved by the deep neural networks and the evolutionary algorithm, respectively. We explore the effect of the Large-margin Gaussian Mixture (L-GM) loss function on distribution learning and design a specialized fitness function based on the similarities among samples to increase diversity. Extensive experiments on benchmark based imbalanced datasets validate the effectiveness of our proposed algorithm, which can generate images with both quality and diversity. Furthermore, the MEDA_LUDE algorithm is also applied to the industrial field and successfully alleviates the imbalanced issue in fabric defect classification.