Batch Normalization (BN) is a highly successful and widely used batch dependent training method. Its use of mini-batch statistics to normalize the activations introduces dependence between samples, which can hurt the training if the mini-batch size is too small, or if the samples are correlated. Several alternatives, such as Batch Renormalization and Group Normalization (GN), have been proposed to address these issues. However, they either do not match the performance of BN for large batches, or still exhibit degradation in performance for smaller batches, or introduce artificial constraints on the model architecture. In this paper we propose the Filter Response Normalization (FRN) layer, a novel combination of a normalization and an activation function, that can be used as a drop-in replacement for other normalizations and activations. Our method operates on each activation map of each batch sample independently, eliminating the dependency on other batch samples or channels of the same sample. Our method outperforms BN and all alternatives in a variety of settings for all batch sizes. FRN layer performs $\approx 0.7-1.0\%$ better on top-1 validation accuracy than BN with large mini-batch sizes on Imagenet classification on InceptionV3 and ResnetV2-50 architectures. Further, it performs $>1\%$ better than GN on the same problem in the small mini-batch size regime. For object detection problem on COCO dataset, FRN layer outperforms all other methods by at least $0.3-0.5\%$ in all batch size regimes.

本文提出了Filter Response Normalization（FRN）层，一种归一化和激活函数的新型组合，可以作为其他归一化和激活函数的替代品；该方法在各种情况下都优于BN和其他替代品，对于具有大型mini-batch的Imagenet分类使用InceptionV3和ResnetV2-50架构，FRN层比BN的top-1验证精度增加约0.7-1.0％；对于小型mini-batch，它比GN的性能增强超过1％；对于COCO数据集上的目标检测问题，FRN层在所有批处理大小各个方面都优于其他方法0.3-0.5％。

Filter Response Normalization层：消除深度神经网络训练中的批次依赖性