Methods › General › Regularization › Auxiliary Batch Normalization
Auxiliary Batch Normalization
Introduced by Cihang Xie et al. in Adversarial Examples Improve Image Recognition
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Auxiliary Batch Normalization is a type of regularization used in adversarial training schemes. The idea is that adversarial examples should have a separate batch normalization components to the clean examples, as they have different underlying statistics.
In Syntology for a different name, 'Batch Normalization', about another paper, arXiv:1502.03167: repository known, no verified implementation (declared_code; repositories: 5 listed of 66 in the graph, strongest link: mentioned on GitHub). The lookup matched a different name in Syntology's graph, 'Batch Normalization' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:1502.03167, while the archive credits arXiv:1911.09665.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Batch and Match (BaM) · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Batch and Match (BaM)') - Batch Styles Standardization (BSS) · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Batch Styles Standardization (BSS)') - Frequency Adaptive Normalization (FAN) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Frequency Adaptive Normalization (FAN)') - Adversarial Batch Normalization (AdvBN) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Adversarial Batch Normalization (AdvBN)') - Auxiliary Task-based OOD Learning (ATOL) · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Auxiliary Task-based OOD Learning (ATOL)') - Style-Adaptive Layer Normalization (SALN) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Style-Adaptive Layer Normalization (SALN)')
Origin paper of this answer, arXiv:1502.03167 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified (of 21 harvested samples) · 5 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: 12 · with a code link: 4 · where Syntology ran a sample: 2 (0 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 12 tagged: 0 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 12 of 12, 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.
-
Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples 23 Aug 2024 · 0 repositories · arXiv:2408.13341
-
EntProp: High Entropy Propagation for Improving Accuracy and Robustness 29 May 2024 · 0 repositories · arXiv:2405.18931
-
Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images 4 Dec 2023 · 0 repositories · arXiv:2312.02253
-
Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain 28 Feb 2023 · 0 repositories · arXiv:2302.14302
-
Easy Batch Normalization 18 Jul 2022 · 0 repositories · arXiv:2207.08940
-
How explainable are adversarially-robust CNNs? 25 May 2022 · 0 repositories · arXiv:2205.13042
-
Fast AdvProp 21 Apr 2022 · 1 repository · arXiv:2204.09838Syntology official (archive's flag): 4 ran · 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) · 0 unverified (of 4 harvested samples)
-
Pyramid Adversarial Training Improves ViT Performance 30 Nov 2021 · 1 repository · arXiv:2111.15121
-
3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation 21 Sep 2021 · 0 repositories · arXiv:2109.10161
-
ALFA: Adversarial Feature Augmentation for Enhanced Image Recognition 1 Jan 2021 · 0 repositories
-
Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery 2 Dec 2020 · 1 repository · arXiv:2012.01981
-
Adversarial Examples Improve Image Recognition 21 Nov 2019 · 6 repositories · arXiv:1911.09665Syntology community repositories only · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
Tasks archive 2025-07-28
20 shown of 22 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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