paper-with-me

홈 › Papers

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

2022-07-26 · Yudi Zhao, Kuangrong Hao, Chaochen Gu, Bing Wei

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.

📄 PDF Abstract BibTeX arXiv:2207.12744

Code (0)

등록된 구현이 없습니다.

Tasks

Diversityimage-classificationImage Classificationimbalanced classification

Similar Papers 제목 키워드 기반

Handling Imbalanced Classification Problems With Support Vector Machines via Evolutionary Bilevel Optimization

2022-04-21 · Alejandro Rosales-Pérez, Salvador García, Francisco Herrera

Support vector machines (SVMs) are popular learning algorithms to deal with binary classification problems. They traditionally assume equal misclassification costs for each class; however, real-world problems may have an…

Bilevel OptimizationBinary ClassificationClassificationimbalanced classification

Fair GANs through model rebalancing for extremely imbalanced class distributions

2023-08-16 · Anubhav Jain, Nasir Memon, Julian Togelius

Deep generative models require large amounts of training data. This often poses a problem as the collection of datasets can be expensive and difficult, in particular datasets that are representative of the appropriate un…

FairnessGenerative Adversarial Network

EvoGAN: An Evolutionary Computation Assisted GAN

2021-10-22 · Feng Liu, HanYang Wang, Jiahao Zhang, Ziwang Fu 외

The image synthesis technique is relatively well established which can generate facial images that are indistinguishable even by human beings. However, all of these approaches uses gradients to condition the output, resu…

Image Generation

Assisted Learning for Organizations with Limited Imbalanced Data

2021-09-20 · Cheng Chen, Jiaying Zhou, Jie Ding, Yi Zhou

In the era of big data, many big organizations are integrating machine learning into their work pipelines to facilitate data analysis. However, the performance of their trained models is often restricted by limited and i…

Decision Making

Rank-Based Learning and Local Model Based Evolutionary Algorithm for High-Dimensional Expensive Multi-Objective Problems

2023-04-19 · Guodong Chen, Jiu Jimmy Jiao, Xiaoming Xue, Zhongzheng Wang

Surrogate-assisted evolutionary algorithms have been widely developed to solve complex and computationally expensive multi-objective optimization problems in recent years. However, when dealing with high-dimensional opti…

Evolutionary Algorithms