Papers › A High-Quality Robust Diffusion Framework for Corrupted Dataset

A High-Quality Robust Diffusion Framework for Corrupted Dataset

28 Nov 2023arXiv:2311.17101archive 2025-07-28

Quan Dao, Binh Ta, Tung Pham, Anh Tran

Developing image-generative models, which are robust to outliers in the training process, has recently drawn attention from the research community. Due to the ease of integrating unbalanced optimal transport (UOT) into adversarial framework, existing works focus mainly on developing robust frameworks for generative adversarial model (GAN). Meanwhile, diffusion models have recently dominated GAN in various tasks and datasets. However, according to our knowledge, none of them are robust to corrupted datasets. Motivated by DDGAN, our work introduces the first robust-to-outlier diffusion. We suggest replacing the UOT-based generative model for GAN in DDGAN to learn the backward diffusion process. Additionally, we demonstrate that the Lipschitz property of divergence in our framework contributes to more stable training convergence. Remarkably, our method not only exhibits robustness to corrupted datasets but also achieves superior performance on clean datasets.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2311.17101")

Code

Syntology Ran 5 of 12 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

VinAIResearch/RDUOT officialmentioned on GitHubpytorchBSD-3-Clause 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

12 samples harvested; 5 ran; 1 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran
7unverified

Licence: 0 of the 12 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 VinAIResearch/RDUOT. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

file_ext VinAIResearch/RDUOT/dataset_tools.py official repository ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · a2b45afa097b55b6 · report
format_time VinAIResearch/RDUOT/dnnlib/util.py official repository ran fingerprinted BSD-3-Clause (permissive) · e595f112049bf2a7 · report
is_image_ext VinAIResearch/RDUOT/dataset_tools.py official repository ran · violated contract BSD-3-Clause (permissive) · 902146c964b18a9a · report
maybe_min VinAIResearch/RDUOT/dataset_tools.py official repository ran · honoured contract BSD-3-Clause (permissive) · dd1dc700e87f36cc · report
tuple_product VinAIResearch/RDUOT/dnnlib/util.py official repository ran fingerprinted BSD-3-Clause (permissive) · efd5d4ab788539f4 · report
ask_yes_no VinAIResearch/RDUOT/dnnlib/util.py official repository unverified BSD-3-Clause (permissive) · 9d31d2c4cd16bb2d · report
calculate_activation_statistics VinAIResearch/RDUOT/pytorch_fid/fid_score.py official repository unverified BSD-3-Clause (permissive) · 8ba5b2e197f0fe1c · report
calculate_frechet_distance VinAIResearch/RDUOT/pytorch_fid/fid_score.py official repository unverified BSD-3-Clause (permissive) · fcdc92d3d2e8edc1 · report
compute_is VinAIResearch/RDUOT/pytorch_fid/inception_score_.py official repository unverified BSD-3-Clause (permissive) · 47c7a1249e324f74 · report
compute_statistics_of_path VinAIResearch/RDUOT/pytorch_fid/score_fid_maker.py official repository unverified BSD-3-Clause (permissive) · 3c62d7eab75c5c83 · report
get_activations VinAIResearch/RDUOT/pytorch_fid/fid_score.py official repository unverified BSD-3-Clause (permissive) · e313af5b82e444c1 · report
num_samples VinAIResearch/RDUOT/datasets_prep/lmdb_datasets.py official repository unverified BSD-3-Clause (permissive) · 4055e76daf3dc938 · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CIFAR-10 RDUOT FID 2.95 #24 of 78 Archive leaderboard report
Image Generation CelebA-HQ 256x256 RDUOT FID 5.6 #5 of 19 Archive leaderboard report
Image Generation CelebA-HQ 256x256 RDUOT Recall 0.38 #5 of 19 Archive leaderboard report
Image Generation STL-10 RDUOT FID 11.5 #3 of 31 Archive leaderboard report
Image Generation STL-10 RDUOT Recall 0.49 #3 of 31 Archive leaderboard report
Image Generation STL-10 RDGAN FID 13.07 #10 of 31 Archive leaderboard report
Image Generation STL-10 RDGAN Recall 0.47 #10 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.

Methods

DiffusionFocus

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