Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to degradation in performance. To solve this problem, in this paper, we concentrate on the study of cross entropy which mostly ignores output scores on incorrect classes. This work discovers that neutralizing predicted probabilities on incorrect classes improves the prediction accuracy for imbalanced image classification. This paper proposes a simple but effective loss named complement cross entropy based on this finding. The proposed loss makes the ground truth class overwhelm the other classes in terms of softmax probability, by neutralizing probabilities of incorrect classes, without additional training procedures. Along with it, this loss facilitates the models to learn key information especially from samples on minority classes. It ensures more accurate and robust classification results on imbalanced distributions. Extensive experiments on imbalanced datasets demonstrate the effectiveness of the proposed method.
翻译:最近,深层学习模型在计算机视觉应用方面取得了巨大成功,依靠大规模类平衡的数据集。然而,由于表现的退化,不平衡的阶级分布仍然限制这些模型的广泛适用性。为了解决这个问题,我们在本文件中集中研究主要忽略不正确的阶级产出分数的交叉酶。这项工作发现,对不正确的阶级预测概率进行中和,可以提高不平衡图像分类的预测准确性。本文件根据这一发现提出一个简单但有效的损失,称为补充交叉星体。拟议的损失使得地面真理阶级在软体概率方面压倒其他阶级,通过排除不正确的阶级的概率,而没有额外的培训程序。除此以外,这一损失还有助于模型学习关键信息,特别是从少数民族阶级的样本中学习信息。它确保不平衡分布的分类结果更加准确和稳健。关于不平衡的数据集的广泛试验证明了拟议方法的有效性。