Papers › CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition

CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition

10 Feb 2023arXiv:2302.05499archive 2025-07-28

Sumyeong Ahn, Jongwoo Ko, Se-Young Yun

Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets. To mitigate this problem, many approaches have aimed to balance among given classes by re-weighting or re-sampling training samples. These re-balancing methods increase the impact of minority classes and reduce the influence of majority classes on the output of models. However, the extracted representations may be of poor quality owing to the limited number of minority samples. To handle this restriction, several methods have been developed that increase the representations of minority samples by leveraging the features of the majority samples. Despite extensive recent studies, no deep analysis has been conducted on determination of classes to be augmented and strength of augmentation has been conducted. In this study, we first investigate the correlation between the degree of augmentation and class-wise performance, and find that the proper degree of augmentation must be allocated for each class to mitigate class imbalance problems. Motivated by this finding, we propose a simple and efficient novel curriculum, which is designed to find the appropriate per-class strength of data augmentation, called CUDA: CUrriculum of Data Augmentation for long-tailed recognition. CUDA can simply be integrated into existing long-tailed recognition methods. We present the results of experiments showing that CUDA effectively achieves better generalization performance compared to the state-of-the-art method on various imbalanced datasets such as CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 1 repository linked to this paper: 18 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; 17 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 14 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 18 ran (1 with no instrument failure; 17 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sumyeongahn/cuda_ltr officialmentioned in paperpytorchSyntology: 20 samples, 18 ran (17 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested: 18 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; 17 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

14ran · our draft was wrong
3ran; the contract check could not run
1ran
2unverified

Licence: 20 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from sumyeongahn/cuda_ltr. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

sumyeongahn/cuda_ltr official repository 20 samples, 18 ran (17 instrument-failed) · 2 unverified
Brightness in 31 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · b8c590bef6e963a5 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
CUDA in 5 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 79325ac79d00a9e4 · report fixture: signature img:Image/0/?, m:int/0/int, n:int/0/int, rand:bool/0/bool, max_d:int/0/int · returned Image · level recorded 2026-09-22
Color in 29 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · d84dd48531aa301a · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Contrast in 5 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · cbaacb95872d184b · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Detail cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 44777427cec78b34 · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
EdgeEnhance cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 2e749a4c531d738f · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
Flip cifar/aug/cuda.py ran; the contract check could not run (RAISES) no licence file found · pointer only · c627a57375b0ed78 · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
GaussianBlur in 9 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · e3a440ead9bd58a5 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Mirror cifar/aug/cuda.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 561d767850eeda60 · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
Rotate in 6 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 524db8e9fbaceab2 · report fixture: signature img:MockImage/0/?, v:int/0/int · returned str · level recorded 2026-09-22
Sharpness cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 1aee0d70df848066 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ShearX in 14 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 9846307204b08173 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ShearY in 14 papers cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 109155544d6d2c48 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Smooth cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 6403d3d16b4a2c9a · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
Solarize cifar/aug/cuda.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 24929112b43ba099 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
TranslateXabs cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 62260bb568ba067f · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
TranslateYabs cifar/aug/cuda.py ran · our draft was wrong no licence file found · pointer only · 9752feef807958b2 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
augment_list cifar/aug/cuda.py ran no licence file found · pointer only · d7ac225abbe34b47 · report fixture: returned list · level recorded 2026-09-22
ResizeCrop cifar/aug/cuda.py unverified no licence file found · pointer only · 8ef3ee0004e5c542 · report
SolarizeAdd cifar/aug/cuda.py unverified no licence file found · pointer only · 7c7fafdfdd722e63 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for CUDA (graph method: CUDA). 24 bricks; individually on a fixture: 22 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; 21 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. CUDA entry · level 1 · ran · our draft was wrong · 79325ac79d00a9e4
  2. augment_list helper · level 1 · ran · d7ac225abbe34b47
  3. AutoContrast data_transform · level 1 · ran · our draft was wrong · 4a0ac9d611e018bc
  4. Brightness data_transform · level 1 · ran · our draft was wrong · b8c590bef6e963a5
  5. Color data_transform · level 1 · ran · our draft was wrong · d84dd48531aa301a
  6. Contrast data_transform · level 1 · ran · our draft was wrong · cbaacb95872d184b
  7. Detail data_transform · level 1 · ran · our draft was wrong · 44777427cec78b34
  8. EdgeEnhance data_transform · level 1 · ran · our draft was wrong · 2e749a4c531d738f
  9. Equalize data_transform · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  10. Flip data_transform · level 1 · ran; the contract check could not run (RAISES) · c627a57375b0ed78
  11. GaussianBlur data_transform · level 1 · ran · our draft was wrong · e3a440ead9bd58a5
  12. Invert data_transform · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  13. Mirror data_transform · level 1 · ran; the contract check could not run (RAISES) · 561d767850eeda60
  14. Posterize data_transform · level 1 · ran · our draft was wrong · 75171b0fbf864dbb
  15. ResizeCrop data_transform · level 0 · unverified · 8ef3ee0004e5c542
  16. Rotate data_transform · level 1 · ran · our draft was wrong · 524db8e9fbaceab2
  17. Sharpness data_transform · level 1 · ran · our draft was wrong · 1aee0d70df848066
  18. ShearX data_transform · level 1 · ran · our draft was wrong · 9846307204b08173
  19. ShearY data_transform · level 1 · ran · our draft was wrong · 109155544d6d2c48
  20. Smooth data_transform · level 1 · ran · our draft was wrong · 6403d3d16b4a2c9a
  21. Solarize data_transform · level 1 · ran; the contract check could not run (RAISES) · 24929112b43ba099
  22. SolarizeAdd data_transform · level 0 · unverified · 7c7fafdfdd722e63
  23. TranslateXabs data_transform · level 1 · ran · our draft was wrong · 62260bb568ba067f
  24. TranslateYabs data_transform · level 1 · ran · our draft was wrong · 9752feef807958b2

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2302.05499") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationLong-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning CIFAR-100-LT (ρ=10) BCL+CUDA Error Rate 35.4 #13 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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