Average Pooling
/ˈævərɪdʒ ˈpuːlɪŋ/
A pooling operation that computes the average value from each window of the feature map.
In italiano: Average PoolingAverage pooling downsamples by taking mean values, preserving more information than max pooling but potentially losing strong activations. Often used as final layer in classification networks.
Examples
- Global average pooling
- Smooth downsampling
- Reducing overfitting