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.
翻译:为解决在不平衡分类任务中生成的图像的质量多样性这一权衡问题,我们研究了在地平层而不是数据层上过度抽样的基于特征的方法,并侧重于搜索潜在特征空间以优化分布。在此基础上,我们建议采用基于Lentant faitUre 分布演进(MEDA_LUDE)算法的 iMprive Estimation 分布测算法,该算法采用联合学习程序,分别使深层神经网络和进化算法优化和演变的潜在特征。我们探讨了大海高山混集(L-GM)损失函数对分布学习的影响,并根据样本之间的相似性设计了专门的健身功能,以增加多样性。根据基于不平衡数据集的基准进行的广泛实验证实了我们拟议的算法的有效性,该算法可以产生质量和多样性的图像。此外,MEDA_LUDE算法还适用于工业领域,并成功地缓解织物缺陷分类中的不平衡问题。