Methods › Computer Vision › Pooling Operations

Pooling Operations

17 methods 8,860 papers tagged archive 2025-07-28

The archive attaches this collection's text per method and the copies differ: 2 distinct texts across 15 of the 17 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.

Text 1, carried by 14 of 17 methods:

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).

Text 2, carried by 1 of 17 methods:

AutoML methods are used to automatically solve machine learning tasks without needing the user to specify or experiment with architectures, hyperparameters and other settings. Below you can find a continuously updating list of AutoML methods.

Also reached at /methods/category/pooling-operation (Papers with Code's slug for this collection; the archive carries no slugs, so this site's is derived from the name).

Methods

All 17 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

Max Pooling – 7,126
Average Pooling – 5,125
Global Average Pooling – 4,076
Spatial Pyramid Pooling – 285
Cascade Corner Pooling – 46
Center Pooling – 46
Adaptive Feature Pooling – 20
Corner Pooling – 12
Generalized Mean Pooling – 6
Strip Pooling – 6
Class-MLP – 3
Hopfield Layer – 3
SoftPool Soft Pooling – 3
Shape Adaptor – 2
Local Importance-based Pooling – 1
RMS Pooling Root-of-Mean-Squared Pooling – 0
TFGW Template based Graph Neural Network with Optimal Transport Distances – 0