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.
In Syntology code not checked for this name. The lookup matched a different name in Syntology's graph, 'FRACTAL' (resolution: token_match), and its answer is about that name only, so it does not say whether this method has code. The archive credits no paper with an arXiv id for this method, so whether this answer (about the paper Syntology's graph keys as openreview_h0RgDbosOj) is about this method is not checked.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 6 · with a code link: 4 · where Syntology ran a sample: 1 (0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 6 tagged: 0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 6 of 6, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
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 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 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