Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs
2021 IEEE/CVF International Conference on Computer Vision (ICCV)(2021)
摘要
In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via global pooling removes all spatial information. Specifically, we demonstrate that positional information is encoded based on the ordering of the channel dimensions, while semantic information is largely not. Following th...
更多查看译文
关键词
Three-dimensional displays,Tensors,Semantics,Neurons,Linear programming,Encoding,Object recognition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要