Spatial Pyramid Pooling

Introduced by He et al. in Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Spatial Pyramid Pooling (SPP) is a pooling layer that removes the fixed-size constraint of the network, i.e. a CNN does not require a fixed-size input image. Specifically, we add an SPP layer on top of the last convolutional layer. The SPP layer pools the features and generates fixed-length outputs, which are then fed into the fully-connected layers (or other classifiers). In other words, we perform some information aggregation at a deeper stage of the network hierarchy (between convolutional layers and fully-connected layers) to avoid the need for cropping or warping at the beginning.

Source: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Semantic Segmentation	96	14.10%
Object Detection	80	11.75%
Object	39	5.73%
Image Segmentation	34	4.99%
Decoder	26	3.82%
Image Classification	19	2.79%
Instance Segmentation	14	2.06%
Real-Time Object Detection	12	1.76%
Deep Learning	12	1.76%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

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

Categories

Add Remove

Pooling Operations