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

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 15 in the graph, strongest link: official). The lookup matched 'stochastic depth' ignoring case. This answer is about arXiv:1603.09382, the paper the archive credits with this method.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1603.09382 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 2 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

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.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 463 · with a code link: 223 · where Syntology ran a sample: 63 (56 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (63 of 463 tagged: 56 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 463, 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.

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