论文标题
周期性局灶性损失
Cyclical Focal Loss
论文作者
论文摘要
跨透明镜软效果损失是用于训练深神经网络的主要损失函数。另一方面，当每个班级的训练样本数量不平衡时，例如长尾数据集中的训练样本数量不平衡时，焦点损失函数已被证明可以提高性能。在本文中，我们引入了一种新型的周期性局灶性损失，并证明它比跨凝结软效果损失或局灶性损失更为普遍。我们描述了周期性局灶性损失背后的直觉，我们的实验提供了证据，表明周期性局灶性损失为平衡，不平衡或长尾数据集提供了出色的性能。我们为CIFAR-10/CIFAR-100，Imagenet，平衡和不平衡的4,000个训练样本版本的CIFAR-10/CIFAR-100以及Imagenet-LT和ImageNet-LT以及来自开放式长尾识别（OLTR）挑战的Places-LT提供了许多实验结果。实施周期性局灶性损失功能只需要几行代码，并且不会增加训练时间。本着可重复性的精神，我们的代码可在\ url {https://github.com/lnsmith54/cfl}上获得。
The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance in the number of training samples in each class, such as in long-tailed datasets. In this paper, we introduce a novel cyclical focal loss and demonstrate that it is a more universal loss function than cross-entropy softmax loss or focal loss. We describe the intuition behind the cyclical focal loss and our experiments provide evidence that cyclical focal loss provides superior performance for balanced, imbalanced, or long-tailed datasets. We provide numerous experimental results for CIFAR-10/CIFAR-100, ImageNet, balanced and imbalanced 4,000 training sample versions of CIFAR-10/CIFAR-100, and ImageNet-LT and Places-LT from the Open Long-Tailed Recognition (OLTR) challenge. Implementing the cyclical focal loss function requires only a few lines of code and does not increase training time. In the spirit of reproducibility, our code is available at \url{https://github.com/lnsmith54/CFL}.
