Distribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification
This work addresses imbalanced classification problems, particularly in industrial applications like fabric defect detection, but is incremental as it builds on existing over-sampling and evolutionary methods.
The paper tackles imbalanced image classification by proposing the MEDA_LUDE algorithm, which uses an evolutionary algorithm and deep neural networks to search latent feature spaces for optimal distributions, resulting in generated images with improved quality and diversity, validated on benchmark datasets and applied to fabric defect classification.
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.