Papers › MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision...

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

24 Apr 2023arXiv:2304.12043archive 2025-07-28

QiHao Zhao, Yangyu Huang, Wei Hu, Fan Zhang, Jun Liu

The recently proposed data augmentation TransMix employs attention labels to help visual transformers (ViT) achieve better robustness and performance. However, TransMix is deficient in two aspects: 1) The image cropping method of TransMix may not be suitable for ViTs. 2) At the early stage of training, the model produces unreliable attention maps. TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model. To address the aforementioned issues, we propose MaskMix and Progressive Attention Labeling (PAL) in image and label space, respectively. In detail, from the perspective of image space, we design MaskMix, which mixes two images based on a patch-like grid mask. In particular, the size of each mask patch is adjustable and is a multiple of the image patch size, which ensures each image patch comes from only one image and contains more global contents. From the perspective of label space, we design PAL, which utilizes a progressive factor to dynamically re-weight the attention weights of the mixed attention label. Finally, we combine MaskMix and Progressive Attention Labeling as our new data augmentation method, named MixPro. The experimental results show that our method can improve various ViT-based models at scales on ImageNet classification (73.8% top-1 accuracy based on DeiT-T for 300 epochs). After being pre-trained with MixPro on ImageNet, the ViT-based models also demonstrate better transferability to semantic segmentation, object detection, and instance segmentation. Furthermore, compared to TransMix, MixPro also shows stronger robustness on several benchmarks. The code is available at https://github.com/fistyee/MixPro.

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 18 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 16 ran (5 with no instrument failure; 11 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 16 samples that ran have no recorded date.

fistyee/mixpro officialmentioned in papermentioned on GitHubpytorchMITSyntology: 18 samples, 16 ran (11 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

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 11 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
6ran · our draft was wrong
5ran; the contract check could not run
4ran
2unverified

Licence: 8 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from fistyee/mixpro. “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. 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.

fistyee/mixpro official repository 18 samples, 16 ran (11 instrument-failed) · 2 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/swin_mlp.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
MaskMix utils.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 03c58083e2ecf6c7 · report fixture: signature samples:Tensor/4/float, flip_samples:Tensor/4/float, alpha:float/0/float, mask_num:int/0/int, scale_:int/0/int, scale:int/0/int, targets:Tensor/1/int, flip_targets:Tensor/1/int, label_smoothing:float/0/float, num_classes:int/0/int · returned tuple · level recorded 2026-09-22
MaskMix utils.py ran MIT (permissive) · 9fc4335dd1dc6864 · report fixture: signature samples:Tensor/4/float, flip_samples:Tensor/4/float, alpha:float/0/float, mask_num:int/0/int, scale_:int/0/int, scale:int/0/int, targets:Tensor/1/int, flip_targets:Tensor/1/int, label_smoothing:float/0/float, num_classes:int/0/int · returned tuple · level recorded 2026-09-25
build_optimizer in 83 papers optimizer.py ran MIT (permissive) here; the stored copy is pointer only · e35a4b2e4114b1a5 · report fixture: signature config:Config/0/?, model:callable/0/? · returned AdamW · level recorded 2026-09-24
build_scheduler in 56 papers lr_scheduler.py ran MIT (permissive) here; the stored copy is pointer only · c02cc4e0b5720211 · report fixture: signature config:Config/0/?, optimizer:SGD/0/?, n_iter_per_epoch:int/0/int · returned LinearLRScheduler · level recorded 2026-09-25
check_keywords_in_name in 32 papers optimizer.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · b0a5beb34716d5a6 · report fixture: signature name:str/0/str, keywords:tuple/1/str · returned bool · level recorded 2026-09-25
checkpoint_filter_fn in 80 papers models/vit.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 5dac11fdc41c896b · report fixture: signature state_dict:dict/0/?, model:callable/0/? · returned dict · level recorded 2026-09-25
create_logger in 172 papers logger.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 80450600f7f09b0a · report fixture: signature output_dir:str/0/str, dist_rank:int/0/int, name:str/0/str · returned Logger · level recorded 2026-09-25
mixup_target in 22 papers utils.py ran · our draft was wrong MIT (permissive) · 08b4e547f3100fc0 · report fixture: signature target:Tensor/1/int, old_target:Tensor/1/int, num_classes:int/0/int, lam:float/0/float, smoothing:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-22
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 1 of 6, arg 1: rank 1, kind int, dtype int64
utils.py ran · our draft was wrong MIT (permissive) · 4728dc2025227bba · report fixture: signature x:Tensor/1/int, num_classes:int/0/int, on_value:float/0/float, off_value:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-22
resize_pos_embed in 102 papers models/vit.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 1dbef2d4da4ee10f · report fixture: signature posemb:Tensor/3/float, posemb_new:Tensor/3/float, num_tokens:int/0/int, gs_new:tuple/1/int · returned Tensor · level recorded 2026-09-25
set_weight_decay in 32 papers optimizer.py ran MIT (permissive) here; the stored copy is pointer only · b33222a09fc93bec · report fixture: signature model:callable/0/?, skip_list:tuple/1/empty, skip_keywords:tuple/1/empty · returned list · level recorded 2026-09-24
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/focal_transformer_v2.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · f9fd6241d935f07b · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_partition_noreshape in 6 papers models/focal_transformer_v2.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · eb8623dc7c37757f · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-24
window_reverse in 296 papers models/swin_mlp.py ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
window_reverse in 296 papers models/focal_transformer_v2.py ran · our draft was wrong MIT (permissive) · fb32094c6dbece71 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
build_model in 469 papers models/build.py unverified MIT (permissive) · 1ecb57de91ce4988 · report
get_config in 203 papers config.py unverified MIT (permissive) · 9b9b6364be5f95f6 · 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 MaskMix (graph method: MaskMix). 3 bricks; individually on a fixture: 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. The assembly has not been run end-to-end.

  1. MaskMix entry · level 1 · ran; the contract check could not run (RAISES) · 03c58083e2ecf6c7
  2. mixup_target helper · level 1 · ran · our draft was wrong · 08b4e547f3100fc0
  3. one_hot helper · level 1 · ran · our draft was wrong · 4728dc2025227bba

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="2304.12043") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationImage AugmentationImage ClassificationImage CroppingInstance SegmentationObject DetectionSemantic Segmentationobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Data Augmentation ImageNet DeiT-B (+MixPro) Accuracy (%) 82.9 #1 of 17 Archive leaderboard report
Data Augmentation ImageNet DeiT-S (+MixPro) Accuracy (%) 81.3 #3 of 17 Archive leaderboard report
Data Augmentation ImageNet DeiT-T (+MixPro) Accuracy (%) 73.8 #17 of 17 Archive leaderboard report
Image Classification ImageNet XCiT-M (+MixPro) Top 1 Accuracy 84.1% #349 of 1060 Archive leaderboard report
Image Classification ImageNet CA-Swin-S (+MixPro) Top 1 Accuracy 83.7% #392 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B (+MixPro) Top 1 Accuracy 82.9% #484 of 1060 Archive leaderboard report
Image Classification ImageNet CA-Swin-T (+MixPro) Top 1 Accuracy 82.8% #494 of 1060 Archive leaderboard report
Image Classification ImageNet PVT-M (+MixPro) Top 1 Accuracy 82.7% #507 of 1060 Archive leaderboard report
Image Classification ImageNet PVT-S (+MixPro) Top 1 Accuracy 81.2% #655 of 1060 Archive leaderboard report
Image Classification ImageNet CaiT-XXS (+MixPro) Top 1 Accuracy 80.6% #692 of 1060 Archive leaderboard report
Image Classification ImageNet PVT-T (+MixPro) Top 1 Accuracy 76.7% #901 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-T (+MixPro) Top 1 Accuracy 73.8% #983 of 1060 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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