Activation Functions

EvoNorms

Introduced by Liu et al. in Evolving Normalization-Activation Layers

EvoNorms are a set of normalization-activation layers that go beyond existing design patterns. Normalization and activation are unified into a single computation graph, its structure is evolved starting from low-level primitives. EvoNorms consist of two series: B series and S series. The B series are batch-dependent and were discovered by our method without any constraint. The S series work on individual samples, and were discovered by rejecting any batch-dependent operations.

Source: Evolving Normalization-Activation Layers

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Classification 1 25.00%
Image Generation 1 25.00%
Instance Segmentation 1 25.00%
Semantic Segmentation 1 25.00%

Components


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

Categories