ConceptGAP / Global Average Pooling
Global Average Pooling
An operation that averages all spatial positions of each channel of a feature map into a single scalar. It is commonly used in classification networks but discards spatial structural information.
Timeline (last 90 days)
Oct 14
The SE module uses global average pooling to compress the spatial information of each channel into a single scalar, then learns channel-wise recalibration weights.
Unverified50%