Brain-inspired Weighted Normalization for CNN Image Classification
Brain-inspired Weighted Normalization for CNN Image Classification
复制标题
DOI：
10.1101/2021.05.20.445029
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Xu Pan;L. G. Sanchez Giraldo;E. Kartal;O. Schwartz
中科院分区：
文献类型：
--
作者：
Xu Pan;L. G. Sanchez Giraldo;E. Kartal;O. Schwartz
我们研究了一种局部标准化范式，即加权标准化，它更好地反映了当前对大脑的理解。具体来说，归一化权重是可训练的，并且具有更现实的环绕池选择。在 Cifar10、Imagenet 和自定义纹理 MNIST 数据集上的图像分类任务中，加权归一化的性能优于其他归一化。当CNN较浅时，优越的性能更加突出。加权归一化的良好性能可能与其高斯化响应的统计效果有关。
We studied a local normalization paradigm, namely weighted normalization, that better reflects the current understanding of the brain. Specifically, the normalization weight is trainable, and has a more realistic surround pool selection. Weighted normalization outperformed other normalizations in image classification tasks on Cifar10, Imagenet and a customized textured MNIST dataset. The superior performance is more prominent when the CNN is shallow. The good performance of weighted normalization may be related to its statistical effect of gaussianizing the responses.