Papers › IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

7 Oct 2023NeurIPS 2023 11arXiv:2310.04780archive 2025-07-28

Zhenglin Huang, Xiaoan Bao, Na Zhang, Qingqi Zhang, Xiaomei Tu, Biao Wu, Xi Yang

Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in real-world scenarios requires not only high accuracy on clean data but also robustness when data distributions shift. While prior methods have proposed that there is a trade-off between accuracy and robustness, we propose IPMix, a simple data augmentation approach to improve robustness without hurting clean accuracy. IPMix integrates three levels of data augmentation (image-level, patch-level, and pixel-level) into a coherent and label-preserving technique to increase the diversity of training data with limited computational overhead. To further improve the robustness, IPMix introduces structural complexity at different levels to generate more diverse images and adopts the random mixing method for multi-scale information fusion. Experiments demonstrate that IPMix outperforms state-of-the-art corruption robustness on CIFAR-C and ImageNet-C. In addition, we show that IPMix also significantly improves the other safety measures, including robustness to adversarial perturbations, calibration, prediction consistency, and anomaly detection, achieving state-of-the-art or comparable results on several benchmarks, including ImageNet-R, ImageNet-A, and ImageNet-O.

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 17 code samples: 16 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 17: 15 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 13 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 14 ran (1 with no instrument failure; 13 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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. 2 of the 15 samples that ran have no recorded date.

hzlsaber/IPMix officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 14 ran (13 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 13 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.

1ran · honoured contract
1ran · violated contract
7ran · our draft was wrong
6ran; the contract check could not run
2unverified

Licence: 1 of the 17 samples is 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 hzlsaber/IPMix. 1 sample is listed last, in a group without a repository. “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.

hzlsaber/IPMix official repository 16 samples, 14 ran (13 instrument-failed) · 2 unverified
add in 19 papers cifar.py ran; the contract check could not run (RAISES) MIT (permissive) · cbb347ae0777187b · report fixture: signature img1:ndarray/4/float, img2:ndarray/4/float, beta:float/0/float · returned ndarray · level recorded 2026-09-22
get_ab cifar.py ran · honoured contract MIT (permissive) · 6b102ac91e94b5e7 · report fixture: signature beta:float/0/float · returned tuple · level recorded 2026-09-22
invert in 12 papers cifar.py ran · our draft was wrong MIT (permissive) · 4cebd5ded62dc91a · report fixture: signature pil_img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
mirror cifar.py ran; the contract check could not run (RAISES) MIT (permissive) · 68e7d0362ce44040 · report fixture: signature pil_img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
multiply cifar.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 1c5c42ef4d6b41ed · report fixture: signature img1:ndarray/2/float, img2:ndarray/2/float, beta:float/0/float · returned ndarray · level recorded 2026-09-22
patch_mixing cifar.py ran · our draft was wrong MIT (permissive) · 464e4c4f1f24b52c · report fixture: signature img:Image/0/?, mixing_pic:Image/0/?, patch_size:int/0/int, mixed_op:callable/0/?, beta:float/0/float · returned Image · level recorded 2026-09-22
random_elems cifar.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 198cba22a2041b0b · report fixture: signature img1:Tensor/3/float, img2:Tensor/3/float, beta:float/0/float · returned Tensor · level recorded 2026-09-22
random_pixels cifar.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · f47705e21f50aab3 · report fixture: signature img1:Tensor/3/float, img2:Tensor/3/float, beta:float/0/float · returned Tensor · level recorded 2026-09-22
rotate in 56 papers cifar.py ran · our draft was wrong MIT (permissive) · 6ff6756edee1c9da · report fixture: signature pil_img:Image/0/?, level:int/0/int · returned Image · level recorded 2026-09-22
shear_x in 43 papers cifar.py ran · our draft was wrong MIT (permissive) · 7dbf6f8a2088e9be · report fixture: signature pil_img:Image/0/?, level:int/0/int · returned Image · level recorded 2026-09-22
shear_y in 37 papers cifar.py ran · our draft was wrong MIT (permissive) · ca2d43eb1a8c083f · report fixture: signature pil_img:Image/0/?, level:int/0/int · returned Image · level recorded 2026-09-22
train in 522 papers imagenet.py ran; the contract check could not run (RAISES) MIT (permissive) · 7914dbaf0adf4d57 · report fixture: returned tuple · level recorded, date not recorded
translate_x in 7 papers cifar.py ran · our draft was wrong MIT (permissive) · d33ba26b62d93326 · report fixture: signature pil_img:Image/0/?, level:int/0/int · returned Image · level recorded 2026-09-22
translate_y in 7 papers cifar.py ran · our draft was wrong MIT (permissive) · 0e7f36bd010453cf · report fixture: signature pil_img:Image/0/?, level:int/0/int · returned Image · level recorded 2026-09-22
augment_input cifar.py unverified MIT (permissive) · d79fa91500ab0018 · report
ipmix cifar.py unverified MIT (permissive) · 4eb2047e53db0d50 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_lr in 91 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 190117b425ab9fe1 · report fixture: signature step:int/0/int, total_steps:int/0/int, lr_max:float/0/float, lr_min:float/0/float · returned float64 · level recorded, date not recorded

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 IPMix (graph method: IPMix). 21 bricks; individually on a fixture: 19 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 15 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. ipmix entry · level 0 · unverified · 4eb2047e53db0d50
  2. augment_input helper · level 0 · unverified · d79fa91500ab0018
  3. patch_mixing data_transform · level 1 · ran · our draft was wrong · 464e4c4f1f24b52c
  4. add helper · level 1 · ran; the contract check could not run (RAISES) · cbb347ae0777187b
  5. equalize helper · level 1 · ran · our draft was wrong · 6d19fda8bae567e8
  6. float_parameter helper · level 1 · ran · honoured contract · 9f75cd937e9f1824
  7. get_ab helper · level 1 · ran · honoured contract · 6b102ac91e94b5e7
  8. int_parameter helper · level 1 · ran · honoured contract · fa762f2f1e10f2e4
  9. invert helper · level 1 · ran · our draft was wrong · 4cebd5ded62dc91a
  10. mirror helper · level 1 · ran; the contract check could not run (RAISES) · 68e7d0362ce44040
  11. multiply helper · level 1 · ran; the contract check could not run (RAISES) · 1c5c42ef4d6b41ed
  12. posterize helper · level 1 · ran · our draft was wrong · 4a0ca5f3edef0f86
  13. random_elems helper · level 1 · ran; the contract check could not run (RAISES) · 198cba22a2041b0b
  14. random_pixels helper · level 1 · ran; the contract check could not run (RAISES) · f47705e21f50aab3
  15. rotate helper · level 1 · ran · our draft was wrong · 6ff6756edee1c9da
  16. sample_level helper · level 1 · ran · violated contract · 5cc8d4764ac07a35
  17. shear_x helper · level 1 · ran · our draft was wrong · 7dbf6f8a2088e9be
  18. shear_y helper · level 1 · ran · our draft was wrong · ca2d43eb1a8c083f
  19. solarize helper · level 1 · ran · our draft was wrong · 78f075a3d806fae7
  20. translate_x helper · level 1 · ran · our draft was wrong · d33ba26b62d93326
  21. translate_y helper · level 1 · ran · our draft was wrong · 0e7f36bd010453cf

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="2310.04780") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Anomaly DetectionData AugmentationDiversity

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