Discussion of: Learning Deep Features for Discriminative Localization

From epsciwiki

Jump to navigation Jump to search

David:

Overall, our approach provides another glimpse into the soul of CNNs.
GAP = Global average Pooling
CAM = Class Activation Map
What are units of table (%)?

Retrieved from "https://wiki.jlab.org/epsciwiki/index.php?title=Discussion_of:_Learning_Deep_Features_for_Discriminative_Localization&oldid=1008"