Khan Salman H, Hayat Munawar, Bennamoun Mohammed, Sohel Ferdous A, Togneri Roberto
IEEE Trans Neural Netw Learn Syst. 2018 Aug;29(8):3573-3587. doi: 10.1109/TNNLS.2017.2732482. Epub 2017 Aug 17.
Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes are abundant, making them an overrepresented majority, and data of other classes are scarce, making them an underrepresented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this paper, we propose a cost-sensitive (CoSen) deep neural network, which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning procedure jointly optimizes the class-dependent costs and the neural network parameters. The proposed approach is applicable to both binary and multiclass problems without any modification. Moreover, as opposed to data-level approaches, we do not alter the original data distribution, which results in a lower computational cost during the training process. We report the results of our experiments on six major image classification data sets and show that the proposed approach significantly outperforms the baseline algorithms. Comparisons with popular data sampling techniques and CoSen classifiers demonstrate the superior performance of our proposed method.
类别不平衡是现实世界中目标检测和分类任务中常见的问题。某些类别的数据丰富，使其成为占比过高的多数类，而其他类别的数据稀缺，使其成为占比过低的少数类。这种不平衡使得分类器难以适当地学习多数类和少数类的判别边界。在本文中，我们提出了一种成本敏感（CoSen）深度神经网络，它可以自动为多数类和少数类学习鲁棒的特征表示。在训练过程中，我们的学习过程联合优化类别相关成本和神经网络参数。所提出的方法无需任何修改即可应用于二分类和多分类问题。此外，与数据级方法不同，我们不改变原始数据分布，这导致训练过程中的计算成本更低。我们报告了在六个主要图像分类数据集上的实验结果，表明所提出的方法明显优于基线算法。与流行的数据采样技术和CoSen分类器的比较证明了我们所提出方法的优越性能。
