[Transformer]CoAtNet:Marrying Convolution and Attention for All Data Sizes
CoAtNet:卷积+注意力用于任意规模的分类任务AbstractSectionIIntroductionSectionIIModelPart1MergingConvolutionandSelf-AttentionPart2VerticalLayputDesignSectionIIIRelatedWorkSectionIVExperimentsPart1MainResultsPart2Ablati