Example: confidence
Learning Deep Features for Discriminative Localization

Learning Deep Features for Discriminative Localization

Back to document page

maps, a technique we call class activation mapping. As illustrated in Fig. 2, global average pooling outputs the spatial average of the feature map of each unit at the last convolutional layer. A weighted sum of these values is used to generate the final output. Similarly, we compute a weighted sum of the feature maps of the last convolutional

  Mapping

Download Learning Deep Features for Discriminative Localization


Information

Domain:

Source:

Link to this page:

Please notify us if you found a problem with this document:

Other abuse

Advertisement

Related search queries