/pytorch-pyramid-pooling

This Module implements Spatial Pyramid Pooling (SPP) and Temporal Pyramid Pooling (TPP) as described in different papers.

Primary LanguagePythonMIT LicenseMIT

Pyramid Pooling implemented in PyTorch

This Module implements Spatial Pyramid Pooling (SPP) and Temporal Pyramid Pooling (TPP) as described in different papers.

SPP-TPP Comparison

Temporal Pyramid Pooling:

Sudholt, Fink: Evaluating Word String Embeddings and LossFunctions for CNN-based Word Spotting

Principle

Given an 2D input Tensor, Temporal Pyramid Pooling divides the input in x stripes which extend through the height of the image and width of roughly (input_width / x). These stripes are then each pooled with max- or avg-pooling to calculate the output.

Animated Principle

TPP Visualization

Spatial Pyramid Pooling:

He, et. al.: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Principle

Given an 2D input Tensor, Spatial Pyramid Pooling divides the input in x² rectangles with height of roughly (input_height / x) and width of roughly (input_width / x). These rectangles are then each pooled with max- or avg-pooling to calculate the output.