Methods › Computer Vision › Image Data Augmentation › AutoAugment
AutoAugment
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
AutoAugment is an automated approach to find data augmentation policies from data. It formulates the problem of finding the best augmentation policy as a discrete search problem. It consists of two components: a search algorithm and a search space.
At a high level, the search algorithm (implemented as a controller RNN) samples a data augmentation policy S, which has information about what image processing operation to use, the probability of using the operation in each batch, and the magnitude of the operation. The policy S is used to train a neural network with a fixed architecture, whose validation accuracy R is sent back to update the controller. Since R is not differentiable, the controller will be updated by policy gradient methods.
The operations used are from PIL, a popular Python image library: all functions in PIL that accept an image as input and output an image. It additionally uses two other augmentation techniques: Cutout and SamplePairing. The operations searched over are ShearX/Y, TranslateX/Y, Rotate, AutoContrast, Invert, Equalize, Solarize, Posterize, Contrast, Color, Brightness, Sharpness, Cutout and Sample Pairing.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1805.09501'). Repositories: 33 listed of 33 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:1805.09501, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1805.09501) is about this method is not checked.
Origin paper of this answer, arXiv:1805.09501 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified (of 43 harvested samples) · 4 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: 60 · with a code link: 45 · where Syntology ran a sample: 20 (17 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (20 of 60 tagged: 17 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 60 of 60, 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.
-
Data Augmentation For Small Object using Fast AutoAugment 10 Jun 2025 · 0 repositories · arXiv:2506.08956
-
Learning Tree-Structured Composition of Data Augmentation 26 Aug 2024 · 1 repository · arXiv:2408.14381
-
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge 16 Jul 2024 · 1 repository · arXiv:2407.11906
-
AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes 8 Feb 2024 · 1 repository · arXiv:2402.05584
-
AutoAugment Input Transformation for Highly Transferable Targeted Attacks 21 Dec 2023 · 0 repositories · arXiv:2312.14218
-
LA3: Efficient Label-Aware AutoAugment 20 Apr 2023 · 1 repository · arXiv:2304.10310
-
RangeAugment: Efficient Online Augmentation with Range Learning 20 Dec 2022 · 1 repository · arXiv:2212.10553
-
Efficient and Effective Augmentation Strategy for Adversarial Training 27 Oct 2022 · 2 repositories · arXiv:2210.15318Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 2 pointer-only (licence)
-
Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers 16 Oct 2022 · 1 repository · arXiv:2210.08458
-
Ultrafast Image Categorization in Biology and Neural Models 7 May 2022 · 1 repository · arXiv:2205.03635
-
Deep AutoAugment 11 Mar 2022 · 1 repository · arXiv:2203.06172
-
SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation 6 Dec 2021 · 0 repositories · arXiv:2112.02862
-
Challenges of Adversarial Image Augmentations 24 Nov 2021 · 0 repositories · arXiv:2111.12427
-
Learning Augmentation Distributions using Transformed Risk Minimization 16 Nov 2021 · 0 repositories · arXiv:2111.08190
-
Improving Model Generalization by Agreement of Learned Representations from Data Augmentation 20 Oct 2021 · 1 repository · arXiv:2110.10536
-
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification 1 Sep 2021 · 1 repository · arXiv:2109.00523
-
Direct Differentiable Augmentation Search 9 Apr 2021 · 1 repository · arXiv:2104.04282
-
Relating Adversarially Robust Generalization to Flat Minima 9 Apr 2021 · 0 repositories · arXiv:2104.04448
-
Robust and Accurate Object Detection via Adversarial Learning 23 Mar 2021 · 3 repositories · arXiv:2103.13886
-
Local Patch AutoAugment with Multi-Agent Collaboration 20 Mar 2021 · 2 repositories · arXiv:2103.11099
-
AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation 10 Mar 2021 · 1 repository · arXiv:2103.05863Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
Faster and Smarter AutoAugment: Augmentation Policy Search Based on Dynamic Data-Clustering 1 Jan 2021 · 0 repositories
-
NOSE Augment: Fast and Effective Data Augmentation Without Searching 1 Jan 2021 · 0 repositories
-
Semantic Aware Data Augmentation for Cell Nuclei Microscopical Images With Artificial Neural Networks 1 Jan 2021 · 0 repositories
-
StackMix: A complementary Mix algorithm 25 Nov 2020 · 0 repositories · arXiv:2011.12618
-
KeepAugment: A Simple Information-Preserving Data Augmentation Approach 23 Nov 2020 · 1 repository · arXiv:2011.11778
-
An Efficient and Scalable Deep Learning Approach for Road Damage Detection 18 Nov 2020 · 2 repositories · arXiv:2011.09577
-
Regularizing Neural Networks via Adversarial Model Perturbation 10 Oct 2020 · 1 repository · arXiv:2010.04925Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples)
-
A Technical Report for VIPriors Image Classification Challenge 17 Jul 2020 · 0 repositories · arXiv:2007.08722
-
Hypernetwork-Based Augmentation 11 Jun 2020 · 0 repositories · arXiv:2006.06320
-
AutoCLINT: The Winning Method in AutoCV Challenge 2019 9 May 2020 · 1 repository · arXiv:2005.04373Syntology official (archive's flag): 3 ran · 3 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; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
On the Generalization Effects of Linear Transformations in Data Augmentation 2 May 2020 · 2 repositories · arXiv:2005.00695Syntology official (archive's flag): 5 ran · 6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples)
-
ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring 1 May 2020 · 1 repository
-
Supervised Contrastive Learning 23 Apr 2020 · 26 repositories · arXiv:2004.11362Syntology community repositories only · 17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 23 harvested samples) · 5 pointer-only (licence)
-
ResNeSt: Split-Attention Networks 19 Apr 2020 · 36 repositories · arXiv:2004.08955Syntology official (archive's flag): 5 ran · 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified (of 48 harvested samples) · 23 pointer-only (licence)
-
UniformAugment: A Search-free Probabilistic Data Augmentation Approach 31 Mar 2020 · 1 repository · arXiv:2003.14348
-
TResNet: High Performance GPU-Dedicated Architecture 30 Mar 2020 · 3 repositories · arXiv:2003.13630
-
Circumventing Outliers of AutoAugment with Knowledge Distillation 25 Mar 2020 · 1 repository · arXiv:2003.11342
-
SuperMix: Supervising the Mixing Data Augmentation 10 Mar 2020 · 2 repositories · arXiv:2003.05034Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
DADA: Differentiable Automatic Data Augmentation 8 Mar 2020 · 1 repository · arXiv:2003.03780Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 5 pointer-only (licence)
-
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network 17 Jan 2020 · 1 repository · arXiv:2001.06268Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified (of 11 harvested samples)
-
GridMask Data Augmentation 13 Jan 2020 · 7 repositories · arXiv:2001.04086
-
Adversarial AutoAugment 24 Dec 2019 · 0 repositories · arXiv:1912.11188
-
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)
-
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring 21 Nov 2019 · 3 repositories · arXiv:1911.09785Syntology official: harvested, nothing ran · 1 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; 1 where Syntology's instrument failed) · 3 unverified (of 4 harvested samples) · 1 pointer-only (licence)
-
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation 16 Nov 2019 · 1 repository · arXiv:1911.06987Syntology 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples)
-
RandAugment: Practical automated data augmentation with a reduced search space 30 Sep 2019 · 19 repositories · arXiv:1909.13719Syntology 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified (of 65 harvested samples) · 17 pointer-only (licence)
-
Automatically Learning Data Augmentation Policies for Dialogue Tasks 27 Sep 2019 · 1 repository · arXiv:1909.12868
-
SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search 16 Aug 2019 · 1 repository · arXiv:1908.06022
-
Greedy AutoAugment 2 Aug 2019 · 2 repositories · arXiv:1908.00704
-
A Fourier Perspective on Model Robustness in Computer Vision 21 Jun 2019 · 0 repositories · arXiv:1906.08988
-
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation 6 Jun 2019 · 2 repositories · arXiv:1906.02611Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
AutoAugment: Learning Augmentation Strategies From Data 1 Jun 2019 · 3 repositories
-
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019 · 144 repositories · arXiv:1905.11946Syntology official: no sample here; runs from other or unrecorded repositories · 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified (of 302 harvested samples) · 113 pointer-only (licence)
-
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules 14 May 2019 · 3 repositories · arXiv:1905.05393Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified (of 18 harvested samples) · 18 pointer-only (licence)
-
Fast AutoAugment 1 May 2019 · 11 repositories · arXiv:1905.00397Syntology official (archive's flag): 9 ran · 37 ran (of which 2 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 0 violated, 19 with no contract checked; 16 where Syntology's instrument failed) · 3 unverified (of 40 harvested samples) · 7 pointer-only (licence)
-
CondConv: Conditionally Parameterized Convolutions for Efficient Inference 10 Apr 2019 · 9 repositories · arXiv:1904.04971
-
MultiGrain: a unified image embedding for classes and instances 14 Feb 2019 · 3 repositories · arXiv:1902.05509Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
Learning data augmentation policies using augmented random search 12 Nov 2018 · 0 repositories · arXiv:1811.04768
-
AutoAugment: Learning Augmentation Policies from Data 24 May 2018 · 33 repositories · arXiv:1805.09501Syntology community repositories only · 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified (of 43 harvested samples) · 4 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 68 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