Methods › General › Regularization › Stochastic Depth

Stochastic Depth

463 papers tagged archive 2025-07-28

Introduced by Gao Huang et al. in Deep Networks with Stochastic Depth

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

Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire ResBlocks during training and bypassing their transformations through skip connections.

Let bₗ ∈ {$0, 1$} denote a Bernoulli random variable, which indicates whether the $l$th ResBlock is active (bₗ = 1) or inactive (bₗ = 0). Further, let us denote the “survival” probability of ResBlock l as pₗ = Pr(bₗ = 1). With this definition we can bypass the $l$th ResBlock by multiplying its function fₗ with bₗ and we extend the update rule to:

Hₗ = ReLU(bₗfₗ(Hₗ₋₁) + id(Hₗ₋₁))

If bₗ = 1, this reduces to the original ResNet update and this ResBlock remains unchanged. If bₗ = 0, the ResBlock reduces to the identity function, Hₗ = id((Hₗ−1).

PaperSourceSee Code · osmr/imgclsmob

Papers archive 2025-07-28

30 shown of 463, 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

20 shown of 371 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
Semantic Segmentation94
Image Classification65
Object Detection52
Segmentation51
Decoder48
image-classification44
object-detection37
Image Segmentation30
Instance Segmentation26
Data Augmentation24
Medical Image Segmentation23
Super-Resolution23
Transfer Learning23
Classification21
Object21
Diagnostic15
Self-Supervised Learning14
GPU13
Image Super-Resolution13
Denoising12

Usage over time archive 2025-07-28

Papers per year tagged with Stochastic Depth: 2016 to 2025, peak 113 113 0 2016: 3 papers 2016 2017: 1 paper 2017 2018: 0 papers 2018 2019: 4 papers 2019 2020: 12 papers 2020 2021: 57 papers 2021 2022: 112 papers 2022 2023: 108 papers 2023 2024: 113 papers 2024 2025: 53 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (463 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