Padé Activation Units

Introduced by Molina et al. in Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks

Parametrized learnable activation function, based on the Padé approximant.

Source: Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks

Read Paper See Code

Paper	Code	Results	Date	Stars

Task	Papers	Share
Cross-Modal Retrieval	1	12.50%
Image-text matching	1	12.50%
Image-to-Text Retrieval	1	12.50%
Retrieval	1	12.50%
Text to Video Retrieval	1	12.50%
Uncertainty Quantification	1	12.50%
Video Retrieval	1	12.50%
Video-Text Retrieval	1	12.50%

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

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