Methods › General › Regularization › ShakeDrop

ShakeDrop

3 papers tagged archive 2025-07-28

Introduced by Yoshihiro Yamada et al. in ShakeDrop Regularization for Deep Residual Learning

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

ShakeDrop regularization extends Shake-Shake regularization and can be applied not only to ResNeXt but also ResNet, WideResNet, and PyramidNet. The proposed ShakeDrop is given as

G(x) = x + (bₗ + α− bₗα)F(x), in train-fwd G(x) = x + (bₗ + β− bₗβ)F(x), in train-bwd G(x) = x + E[bₗ + α− bₗα]F(x), in test

where bₗ is a Bernoulli random variable with probability P(bₗ = 1) = E[bₗ ] = pₗ given by the linear decay rule in each layer, and α and β are independent uniform random variables in each element.

The most effective ranges of α and β were experimentally found to be different from those of Shake-Shake, and are α = 0, β∈[0, 1] and α∈[−1, 1], β∈[0, 1].

PaperSourceSee Code · owruby/shake-drop_pytorch

Papers archive 2025-07-28

3 shown of 3, 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.

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.

TaskPapers
Data Augmentation2
Image Classification2
image-classification2
Domain Generalization1
General Classification1
Knowledge Distillation1
Object Detection1
object-detection1

Usage over time archive 2025-07-28

Papers per year tagged with ShakeDrop: 2018 to 2020, peak 1 1 0 2018: 1 paper 2018 2019: 1 paper 2019 2020: 1 paper 2020
Papers per year the archive tags with this method, by the paper's archive date (3 dated). Bars are counts, not a trend claim.

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

Regularization

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