Methods › General › Regularization › Shake-Shake Regularization
Shake-Shake Regularization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Shake-Shake Regularization aims to improve the generalization ability of multi-branch networks by replacing the standard summation of parallel branches with a stochastic affine combination. A typical pre-activation ResNet with 2 residual branches would follow this equation:
xᵢ₊₁ = xᵢ + ℱ(xᵢ, 𝒲ᵢ⁽¹⁾) + ℱ(xᵢ, 𝒲ᵢ⁽²⁾)
Shake-shake regularization introduces a random variable αᵢ following a uniform distribution between 0 and 1 during training:
xᵢ₊₁ = xᵢ + αℱ(xᵢ, 𝒲ᵢ⁽¹⁾) + (1-α)ℱ(xᵢ, 𝒲ᵢ⁽²⁾)
Following the same logic as for dropout, all αᵢ are set to the expected value of 0.5 at test time.
In Syntology repository known, no verified implementation (declared_code; repositories: 13 listed of 13 in the graph, strongest link: official). The lookup matched a paper by its title, arXiv:1705.07485, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1705.07485) is about this method is not checked.
Origin paper of this answer, arXiv:1705.07485 (its page on this site · its page on Syntology).
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: 5 · with a code link: 4 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 5 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 5 of 5, 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.
-
CondConv: Conditionally Parameterized Convolutions for Efficient Inference 10 Apr 2019 · 9 repositories · arXiv:1904.04971
-
Data Augmentation using Random Image Cropping and Patching for Deep CNNs 22 Nov 2018 · 1 repository · arXiv:1811.09030
-
Averaging Weights Leads to Wider Optima and Better Generalization 14 Mar 2018 · 17 repositories · arXiv:1803.05407Syntology official (archive's flag): 2 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 4 pointer-only (licence)
-
ShakeDrop regularization 1 Jan 2018 · 0 repositories
-
Shake-Shake regularization 21 May 2017 · 13 repositories · arXiv:1705.07485
Tasks archive 2025-07-28
8 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 |
|---|---|
| Image Classification | 2 |
| Data Augmentation | 1 |
| General Classification | 1 |
| Image Augmentation | 1 |
| Image Cropping | 1 |
| Object Detection | 1 |
| Retrieval | 1 |
| Stochastic Optimization | 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