Papers › DataDAM: Efficient Dataset Distillation with Attention Matching

DataDAM: Efficient Dataset Distillation with Attention Matching

29 Sep 2023ICCV 2023 1arXiv:2310.00093archive 2025-07-28

Ahmad Sajedi, Samir Khaki, Ehsan Amjadian, Lucy Z. Liu, Yuri A. Lawryshyn, Konstantinos N. Plataniotis

Researchers have long tried to minimize training costs in deep learning while maintaining strong generalization across diverse datasets. Emerging research on dataset distillation aims to reduce training costs by creating a small synthetic set that contains the information of a larger real dataset and ultimately achieves test accuracy equivalent to a model trained on the whole dataset. Unfortunately, the synthetic data generated by previous methods are not guaranteed to distribute and discriminate as well as the original training data, and they incur significant computational costs. Despite promising results, there still exists a significant performance gap between models trained on condensed synthetic sets and those trained on the whole dataset. In this paper, we address these challenges using efficient Dataset Distillation with Attention Matching (DataDAM), achieving state-of-the-art performance while reducing training costs. Specifically, we learn synthetic images by matching the spatial attention maps of real and synthetic data generated by different layers within a family of randomly initialized neural networks. Our method outperforms the prior methods on several datasets, including CIFAR10/100, TinyImageNet, ImageNet-1K, and subsets of ImageNet-1K across most of the settings, and achieves improvements of up to 6.5% and 4.1% on CIFAR100 and ImageNet-1K, respectively. We also show that our high-quality distilled images have practical benefits for downstream applications, such as continual learning and neural architecture search.

PaperPDFConference PDFCodeCode 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 43 code samples harvested from 1 repository linked to this paper: 35 ran (of which 15 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 16 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 15 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 43 samples from 1 repository, 35 ran (19 with no instrument failure; 16 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

datadistillation/datadam officialmentioned in paperpytorchSyntology: 43 samples, 35 ran (16 instrument-failed) · 8 unverified report
Guang000/Awesome-Dataset-Distillation mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling (arXiv:2507.03331; that paper's own run record: 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); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

43 samples harvested: 35 ran (of which 15 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 16 where Syntology's instrument failed) · 8 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.

15ran · our draft was wrong
1ran; the contract check could not run
19ran
8unverified

Licence: 43 of the 43 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 datadistillation/datadam. “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”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

datadistillation/datadam official repository 43 samples, 35 ran (16 instrument-failed) · 8 unverified
AlexNet in 8 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3a77313e815f4446 · report fixture: returned AlexNet · level recorded 2026-09-22
AlexNetBN main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · e115409c4e00e969 · report fixture: returned AlexNetBN · level recorded 2026-09-22
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4e14cbaa48d8cc75 · report fixture: returned Attention · level recorded 2026-09-22
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
main_DataDAM.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 0e55526126f5ac6a · report fixture: returned BasicBlock · level recorded 2026-09-22
BasicBlock_AP main_DataDAM.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 881b5b714601c990 · report fixture: returned BasicBlock_AP · level recorded 2026-09-22
ConvNet in 13 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · cacbe6eda6096eec · report fixture: returned ConvNet · level recorded 2026-09-22
FeedForward in 198 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 450f5b303bbc3417 · report fixture: returned FeedForward · level recorded 2026-09-22
LeNet in 5 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8ac93772f8b62582 · report fixture: returned LeNet · level recorded 2026-09-22
MLP in 375 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2632cd271d2b1d41 · report fixture: returned MLP · level recorded 2026-09-22
PreNorm in 34 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9b66b60a7704b891 · report fixture: returned PreNorm · level recorded 2026-09-22
ResNet in 139 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 87825ad2fefad289 · report fixture: returned ResNet · level recorded 2026-09-22
ResNet18 in 174 papers main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · 7c9efcd20eaa83da · report fixture: signature channel:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-22
ResNet18BN main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · a356b663f3ac431b · report fixture: signature channel:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-22
ResNet18BN_AP main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · 2c1568b6ce72e1c9 · report fixture: signature channel:int/0/int, num_classes:int/0/int · returned ResNet_AP · level recorded 2026-09-22
ResNet_AP main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 812296fd5aaf4e41 · report fixture: returned ResNet_AP · level recorded 2026-09-22
Swish in 30 papers
census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
main_DataDAM.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7266bcefd6533fab · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
TensorDataset main_DataDAM.py ran no licence file found · pointer only · 3c2e1728144bb05d · report fixture: returned TensorDataset · level recorded 2026-09-22
Transformer in 173 papers main_DataDAM.py ran no licence file found · pointer only · fd9a30700758c3bc · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
VGG in 16 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · ab31aadcda7a9603 · report fixture: returned VGG · level recorded 2026-09-22
VGG11 in 36 papers main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · d0f0d585cc626bd7 · report fixture: signature channel:int/0/int, num_classes:int/0/int · returned VGG · level recorded 2026-09-22
VGG11BN in 29 papers main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · 9e7a6f74075e564f · report fixture: signature channel:int/0/int, num_classes:int/0/int · returned VGG · level recorded 2026-09-22
ViT in 10 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · d5630ef1d9988d5a · report fixture: returned ViT · level recorded 2026-09-22
ViTModel main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · 2c7c8872bf76354a · report fixture: signature im_size:int/0/int, num_classes:int/0/int · returned ViT · level recorded 2026-09-22
get_attention in 13 papers main_DataDAM.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · cd229917ccd77249 · report fixture: signature feature_set:Tensor/4/float, param:int/0/int, exp:int/0/int, norm:str/0/str · returned Tensor · level recorded 2026-09-22
get_default_convnet_setting main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · 19457c962ab49bdd · report fixture: returned tuple · level recorded 2026-09-22
get_eval_pool main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · 21792c325f5769e6 · report fixture: signature eval_mode:str/0/str, model:str/0/str, model_eval:str/0/str · returned list · level recorded 2026-09-22
get_time in 20 papers main_DataDAM.py ran · metamorphic tier: deterministic no licence file found · pointer only · e98b4502952690a9 · report fixture: returned str · level recorded 2026-09-22
rand_brightness in 25 papers
census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · 1cad5517390bb5b5 · report fixture: signature x:Tensor/4/float, param:Param/0/? · returned Tensor · level recorded 2026-09-22
rand_contrast in 7 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · b551aeb91085de7c · report fixture: signature x:Tensor/4/float, param:Param/0/? · returned Tensor · level recorded 2026-09-22
rand_crop in 6 papers main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · e2b5b619f5661137 · report fixture: signature x:Tensor/4/float, param:Param/0/? · returned Tensor · level recorded 2026-09-22
rand_cutout in 7 papers
census: 6 implementations from 6 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · e7e9168fac4fe2a7 · report fixture: signature x:Tensor/4/float, param:Param/0/? · returned Tensor · level recorded 2026-09-22
rand_flip in 6 papers main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · ab6f69dd3438d7cf · report fixture: signature x:Tensor/4/float, param:Param/0/? · returned Tensor · level recorded 2026-09-22
rand_rotate in 5 papers main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · 94b4020af89df30d · report fixture: signature x:Tensor/4/float, param:ParamConfig/0/? · returned Tensor · level recorded 2026-09-22
rand_saturation in 24 papers
census: 6 implementations from 9 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · c464d3d7b7e65175 · report fixture: signature x:Tensor/4/float, param:ParamConfig/0/? · returned Tensor · level recorded 2026-09-22
rand_scale in 10 papers main_DataDAM.py ran · our draft was wrong no licence file found · pointer only · ce2cd9ed7e80e7e5 · report fixture: signature x:Tensor/4/float, param:ParamConfig/0/? · returned Tensor · level recorded 2026-09-22
ParamDiffAug main_DataDAM.py unverified no licence file found · pointer only · 59602e0b7b844b46 · report
epoch in 23 papers main_DataDAM.py unverified no licence file found · pointer only · d420983fabce48c3 · report
evaluate_synset main_DataDAM.py unverified no licence file found · pointer only · 4116a89fdeeb7778 · report
get_dataset in 285 papers main_DataDAM.py unverified no licence file found · pointer only · 4fa3d915bca9fa98 · report
get_network in 100 papers main_DataDAM.py unverified no licence file found · pointer only · 736fa42944cf4c63 · report
main in 235 papers main_DataDAM.py unverified no licence file found · pointer only · a34fe411a5565754 · report
set_seed_DiffAug main_DataDAM.py unverified no licence file found · pointer only · e11ae486efd933fd · 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 DataDAM (graph method: DataDAM). 44 bricks; individually on a fixture: 36 ran (of which 15 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 1 violated, 19 with no contract checked; 16 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. main entry · level 0 · unverified · a34fe411a5565754
  2. DiffAugment data_transform · level 0 · unverified · 351e66f1c6171f1f
  3. ParamDiffAug helper · level 0 · unverified · 59602e0b7b844b46
  4. evaluate_synset metric · level 0 · unverified · 4116a89fdeeb7778
  5. get_attention helper · level 1 · ran; the contract check could not run (RAISES) · cd229917ccd77249
  6. get_dataset data_transform · level 0 · unverified · 4fa3d915bca9fa98
  7. get_eval_pool helper · level 1 · ran · our draft was wrong · 21792c325f5769e6
  8. get_network model · level 0 · unverified · 736fa42944cf4c63
  9. get_time helper · level 1 · ran · e98b4502952690a9
  10. set_seed_DiffAug helper · level 0 · unverified · e11ae486efd933fd
  11. TensorDataset helper · level 1 · ran · 3c2e1728144bb05d
  12. epoch update_rule · level 0 · unverified · d420983fabce48c3
  13. AlexNet helper · level 1 · ran · 3a77313e815f4446
  14. AlexNetBN helper · level 1 · ran · e115409c4e00e969
  15. ConvNet helper · level 1 · ran · cacbe6eda6096eec
  16. LeNet helper · level 1 · ran · 8ac93772f8b62582
  17. MLP helper · level 1 · ran · 2632cd271d2b1d41
  18. ResNet18 helper · level 1 · ran · our draft was wrong · 7c9efcd20eaa83da
  19. ResNet18BN helper · level 1 · ran · our draft was wrong · a356b663f3ac431b
  20. ResNet18BN_AP helper · level 1 · ran · our draft was wrong · 2c1568b6ce72e1c9
  21. VGG11 helper · level 1 · ran · our draft was wrong · d0f0d585cc626bd7
  22. VGG11BN helper · level 1 · ran · our draft was wrong · 9e7a6f74075e564f
  23. ViTModel helper · level 1 · ran · our draft was wrong · 2c7c8872bf76354a
  24. get_default_convnet_setting helper · level 1 · ran · 19457c962ab49bdd
  25. Swish helper · level 1 · ran · 7266bcefd6533fab
  26. BasicBlock helper · level 1 · ran · 0e55526126f5ac6a
  27. ResNet helper · level 1 · ran · 87825ad2fefad289
  28. BasicBlock_AP helper · level 1 · ran · 881b5b714601c990
  29. ResNet_AP helper · level 1 · ran · 812296fd5aaf4e41
  30. VGG helper · level 1 · ran · ab31aadcda7a9603
  31. ViT helper · level 1 · ran · d5630ef1d9988d5a
  32. Transformer helper · level 1 · ran · fd9a30700758c3bc
  33. pair helper · level 1 · ran · violated contract · 6ba8cee9f5daea41
  34. Attention helper · level 1 · ran · 4e14cbaa48d8cc75
  35. FeedForward helper · level 1 · ran · 450f5b303bbc3417
  36. PreNorm helper · level 1 · ran · 9b66b60a7704b891
  37. rand_brightness helper · level 1 · ran · our draft was wrong · 1cad5517390bb5b5
  38. rand_contrast helper · level 1 · ran · our draft was wrong · b551aeb91085de7c
  39. rand_crop helper · level 1 · ran · our draft was wrong · e2b5b619f5661137
  40. rand_cutout helper · level 1 · ran · our draft was wrong · e7e9168fac4fe2a7
  41. rand_flip helper · level 1 · ran · our draft was wrong · ab6f69dd3438d7cf
  42. rand_rotate helper · level 1 · ran · our draft was wrong · 94b4020af89df30d
  43. rand_saturation helper · level 1 · ran · our draft was wrong · c464d3d7b7e65175
  44. rand_scale helper · level 1 · ran · our draft was wrong · ce2cd9ed7e80e7e5

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="2310.00093") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continual LearningDataset DistillationNeural Architecture Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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