SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.04747 · ICCV · 2023

When to Learn What: Model-Adaptive Data Augmentation Curriculum

Tianyi Zhou, Jieyu Zhang, Chengkai Hou

arXiv · PDF · Open in the Atlas

Code that ran

23 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 20 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2309.04747.json · badge: /api/ran/2309.04747.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
JackHck/MADAug community
Papers with Code archive
23 ran · 1 no recorded run
FunctionStatusWhere it lives
AutoContrast Ran
ran; our contract draft was wrong, not the code
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("231310cc94015850")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Brightness Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("75ed82aa32df43b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Color Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("de171eb052fc4c75")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Contrast Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("c30c561be0548783")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Cutout Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("1b34ee8bad446181")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CutoutAbs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("6485359d69298193")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Equalize Ran
ran; our contract draft was wrong, not the code
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("8c6c7db6bb443e07")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Flip Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("342c3edf6c22ff5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Identity Ran
ran, violated the contract we drafted
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("5adb748bc6564a2e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Invert Ran
ran; our contract draft was wrong, not the code
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("065cd9cb0840a037")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

PolicyHistory Ran
ran on a synthesized input · constructed an object; no result was computed
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("b4ab295dcde498bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Posterize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("5728c22d6623c134")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Rotate Ran
ran; our contract draft was wrong, not the code
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("21c6427b09f14649")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Sharpness Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("e3d6ffe8ddee37bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ShearX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("f6ae043c08b1cad6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ShearY Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("b6880407116d0216")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Solarize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("4f6921b7200a8bda")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TranslateX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("097a4e4e1779e301")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TranslateY Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("44a5c51db514e860")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_augment Ran
ran; our contract draft was wrong, not the code
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("0a90a9e0ab96ceaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_augment Ran
ran; our contract draft was wrong, not the code
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("c491601c2e8534c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

perturb_param Ran
ran, honoured the contract we drafted
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("6f6ba9be02bf7c9c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

stop_gradient Ran
ran; our contract draft was wrong, not the code
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("f86c9dd77bb5afe7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

MDAAug Not yet run
unverified (harvested, no recorded run)
JackHck/MADAug/adaptive_augmentor.py
pointer only (licence: NONE) · get_code("d8765ed2b78dd264")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JackHck/MADAug when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 16 are also present in other papers whose code we hold (16 with at least one paper dated earlier, 0 the same month, 4 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
AutoContrast
brick of this paper's assembly: helper
14 other papers
7 dated earlier, 7 later · 4 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 11 more not named here
ShearX
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
and 5 more not named here
ShearY
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
and 5 more not named here
TranslateX
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
and 5 more not named here
Equalize
brick of this paper's assembly: helper
6 other papers
6 dated earlier · 4 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 3 more not named here
Invert
brick of this paper's assembly: helper
6 other papers
6 dated earlier · 4 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 3 more not named here
Brightness
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 1 more not named here
Color
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 1 more not named here
Contrast
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 1 more not named here
CutoutAbs
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 1 more not named here
Posterize
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 1 more not named here
Sharpness
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 1 more not named here
Solarize
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 1 more not named here
Cutout
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 2 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2103.05863 (2021-03)
AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation
Rotate
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 3 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2103.05863 (2021-03)
AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation
TranslateY
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 2 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2103.05863 (2021-03)
AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Data augmentation (DA) is widely used to improve the generalization of neural networks by enforcing the invariances and symmetries to pre-defined transformations applied to input data. However, a fixed augmentation policy may have different effects on each sample in different training stages but existing approaches cannot adjust the policy to be adaptive to each sample and the training model. In this paper, we propose "Model-Adaptive Data Augmentation (MADAug)" that jointly trains an augmentation policy network to teach the model "when to learn what". Unlike previous work, MADAug selects augmentation operators for each input image by a model-adaptive policy varying between training stages, producing a data augmentation curriculum optimized for better generalization. In MADAug, we train the policy through a bi-level optimization scheme, which aims to minimize a validationset loss of a model trained using the policy-produced data augmentations. We conduct an extensive evaluation of MADAug on multiple image classification tasks and network architectures with thorough comparisons to existing DA approaches. MADAug outperforms or is on par with other baselines and exhibits better fairness: it brings improvement to all classes and more to the difficult ones. Moreover, MADAug learned policy shows better performance when transferred to fine-grained datasets. In addition, the auto-optimized policy in MADAug gradually introduces increasing perturbations and naturally forms an easy-to-hard curriculum. Our code is available at https: //github.com/JackHck/MADAug.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.04747")
get_code_for_paper("2309.04747")
have("2309.04747")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2309.04747.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2309.04747.svg)](https://syntology.ai/paper/2309.04747)

Connect an agent — have() is free.