Pooling Operations

Max Pooling

Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually used after a convolutional layer. It adds a small amount of translation invariance - meaning translating the image by a small amount does not significantly affect the values of most pooled outputs.

Image Source: here


Paper Code Results Date Stars


Task Papers Share
Semantic Segmentation 68 8.74%
Image Segmentation 40 5.14%
Denoising 33 4.24%
Decoder 28 3.60%
Image Generation 27 3.47%
Image Classification 25 3.21%
Medical Image Segmentation 20 2.57%
Self-Supervised Learning 19 2.44%
Object Detection 16 2.06%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign