Methods › Computer Vision › Image Model Blocks › Fractal Block
Fractal Block
Introduced by Gustav Larsson et al. in FractalNet: Ultra-Deep Neural Networks without Residuals
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 f₁(z) = conv(z) is a convolutional layer, we then have recursive fractals of the form:
f_(C+1)(z) = [(f_C∘f_C)(z)] ⊕[conv(z)]
Where C is the number of columns. For the join layer (green in Figure), we use the element-wise mean rather than concatenation or addition.
Papers archive 2025-07-28
6 shown of 6, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Handwritten Bangla Character Recognition Using The State-of-Art Deep Convolutional Neural Networks 28 Dec 2017 · 1 repository · arXiv:1712.09872
-
CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior 30 Oct 2017 · 0 repositories · arXiv:1710.11176
-
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations 27 Oct 2017 · 0 repositories · arXiv:1710.10121
-
SMASH: One-Shot Model Architecture Search through HyperNetworks 17 Aug 2017 · 1 repository · arXiv:1708.05344
-
Deep Convolutional Neural Network Design Patterns 2 Nov 2016 · 1 repository · arXiv:1611.00847
-
FractalNet: Ultra-Deep Neural Networks without Residuals 24 May 2016 · 4 repositories · arXiv:1605.07648Syntology ran 4 of 6 samples · 2 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
6 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Deep Learning | 1 |
| Image Classification | 1 |
| Neural Architecture Search | 1 |
| Object Recognition | 1 |
| Translation | 1 |
| model | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections