A Class Imbalance Loss for Imbalanced Object Recognition

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing 2020, Vol.13, p.2778-2792
• Main Authors: Zhang, Linbin, Zhang, Caiguang, Quan, Sinong, Xiao, Huaxin, Kuang, Gangyao, Liu, Li
• Format: Article
• Language: English
• Subjects: Adaptation; Algorithms; Artificial neural networks; Computer architecture; Convolutional neural networks (CNNs); Datasets; Deep learning; Entropy; Entropy (Information theory); few-shot learning; image classification; imbalanced learning; Learning; loss functions; Marine vehicles; Neural networks; Object detection; Object recognition; Pattern recognition; Ships; Synthetic aperture radar; Target acquisition; Target recognition; Task analysis; Training
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2020.2995703

The class imbalance problem exists widely in vision data. In these imbalanced datasets, the majority classes dominate the loss and influence the gradient. Hence, these datasets have a significantly negative impact on the performance of many state-of-the-art methods. In this article, we propose a class imbalance loss (CI loss) to handle this problem. To distinguish imbalanced datasets in accordance with the extent of imbalance, we also define an imbalance degree that works as a decision index factor in the CI loss. Because the minority classes with fewer samples probably lose chances in descending the gradient in the training process, CI loss is introduced to make these minority classes descend further than the majority classes. In view of the imbalanced distribution of data in few-shot learning, a method for generating an imbalanced few-shot learning dataset is presented in this article. We conducted a large number of experiments in the MiniImageNet dataset, which showed the effectiveness of an algorithm for model-agnostic metalearning for rapid adaptation with CI loss. In the problem of detecting 15 ship categories, our loss function is transplanted to a rotational region convolutional neural network detection method and a cascade network architecture and achieves higher mean average precision than focal loss and cross-entropy loss. In addition, the Mixed National Institute of Standards and Technology dataset and the Moving and Stationary Target Acquisition and Recognition dataset are sampled to imbalance datasets to verify the effectiveness of CI loss.