Pooling Operations

Pooling Operations are used to pool features together, often downsampling the feature map to a smaller size. They can also induce favourable properties such as translation invariance in image classification, as well as bring together information from different parts of a network in tasks like object detection (e.g. pooling different scales). Below you can find a continuously updating list of pooling operations.

Max Pooling
2000 2501
Average Pooling
2000 1703
Global Average Pooling
2013 1382
Spatial Pyramid Pooling
2014 73
Center Pooling
2019 10
Cascade Corner Pooling
2019 10
Adaptive Feature Pooling
2018 6
Corner Pooling
2018 6
Generalized Mean Pooling
2000 2
Local Importance-based Pooling
2019 1
Hopfield Layer
2020 1
RMS Pooling
2000 0