首页>
外国专利>
GENERATING SHIFT-INVARIANT NEURAL NETWORK FEATURE MAPS AND OUTPUTS
GENERATING SHIFT-INVARIANT NEURAL NETWORK FEATURE MAPS AND OUTPUTS
展开▼
机译:生成移位不变神经网络的功能映射和输出
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present disclosure relates to systems, methods, and non-transitory computer readable media for generating shift-resilient neural network outputs based on utilizing a dense pooling layer, a low-pass filter layer, and a downsampling layer of a neural network. For example, the disclosed systems can generate a pooled feature map utilizing a dense pooling layer to densely pool feature values extracted from an input. The disclosed systems can further apply a low-pass filter to the pooled feature map to generate a shift-adaptive feature map. In addition, the disclosed systems can downsample the shift-adaptive feature map utilizing a downsampling layer. Based on the downsampled, shift-adaptive feature map, the disclosed systems can generate shift-resilient neural network outputs such as digital image classifications.
展开▼