A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is
In this work, we revisit the global average pooling layer proposed in  , and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that can be applied to a variety of tasks. Despite the apparent simplicity of global average pooling,doi:10.1109/cvpr.2016.319 dblp:conf/cvpr/ZhouKLOT16 fatcat:4mmwelc4xbgr5gf4erobt5cmpi