Viet-Anh on Software Logo

What is: Fractal Block?

SourceFractalNet: Ultra-Deep Neural Networks without Residuals
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A Fractal Block is an image model block that utilizes an expansion rule that yields a structural layout of truncated fractals. For the base case where f_1(z)=conv(z)f\_{1}\left(z\right) = \text{conv}\left(z\right) is a convolutional layer, we then have recursive fractals of the form:

f_C+1(z)=[(f_Cf_C)(z)][conv(z)] f\_{C+1}\left(z\right) = \left[\left(f\_{C}\circ{f\_{C}}\right)\left(z\right)\right] \oplus \left[\text{conv}\left(z\right)\right]

Where CC is the number of columns. For the join layer (green in Figure), we use the element-wise mean rather than concatenation or addition.