Papers › DenoiseRep: Denoising Model for Representation Learning

DenoiseRep: Denoising Model for Representation Learning

13 Jun 2024arXiv:2406.08773archive 2025-07-28

Zhengrui Xu, Guan'an Wang, Xiaowen Huang, Jitao Sang

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors". In this paper, we propose a novel Denoising Model for Representation Learning (DenoiseRep) to improve feature discrimination with joint feature extraction and denoising. DenoiseRep views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, DenoiseRep fuses the parameters of feature extraction and denoising layers, and theoretically demonstrates its equivalence before and after the fusion, thus making feature denoising computation-free. DenoiseRep is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures.

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 22 code samples harvested from 1 repository linked to this paper: 17 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 6 honoured, 2 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 17 ran (13 with no instrument failure; 4 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. 1 of the 17 samples that ran has no recorded date.

wangguanan/denoiserep officialmentioned in paperpytorchApache-2.0Syntology: 22 samples, 17 ran (4 instrument-failed) · 5 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

22 samples harvested: 17 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 6 honoured, 2 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 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.

6ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
5ran
5unverified

Licence: 6 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 wangguanan/denoiserep. “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 3 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 2, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape; for 1, 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.

wangguanan/denoiserep official repository 22 samples, 17 ran (4 instrument-failed) · 5 unverified
DenoiseLayer denoiserep_op/denoiserep/denoise_layer.py ran Apache-2.0 (permissive) · cc79b939ebdd3e56 · report fixture: returned DenoiseLayer · level recorded 2026-09-22
SinusoidalPositionEmbeddings in 8 papers
census: 5 implementations from 5 papers, 3 distinct outputs on one shared input
denoiserep_op/denoiserep/denoise_layer.py ran fingerprinted Apache-2.0 (permissive) · 86b013bf84701f06 · report fixture: returned SinusoidalPositionEmbeddings · level recorded 2026-09-22
_linear_beta_schedule denoiserep_op/denoiserep/denoise_layer.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 742e7c8b503f4e2f · report fixture: signature timesteps:int/0/int, beta_start:float/0/float, beta_end:float/0/float · returned Tensor · level recorded 2026-09-22
auto_resume_helper in 27 papers Classification/imagenet/Swin-Transformer/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 0c32459bef92ff8c · report fixture: signature output_dir:str/0/str · returned str · level recorded 2026-09-25
auto_resume_helper in 27 papers Classification/imagenet/Swin-Transformer/utils_simmim.py ran · our draft was wrong Apache-2.0 (permissive) · 973ac6b787475389 · report fixture: signature output_dir:str/0/str, logger:Logger/0/? · returned str · level recorded 2026-09-24
build_optimizer in 83 papers Classification/imagenet/Swin-Transformer/optimizer.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 9fe330952c4ee761 · report fixture: signature config:Config/0/?, model:callable/0/?, simmim:bool/0/bool, is_pretrain:bool/0/bool · returned AdamW · level recorded 2026-09-24
build_scheduler in 56 papers Classification/imagenet/Swin-Transformer/lr_scheduler.py ran Apache-2.0 (permissive) · 016895042cc7e7ef · report fixture: signature config:Config/0/?, optimizer:SGD/0/?, n_iter_per_epoch:int/0/int · returned CosineLRScheduler · level recorded 2026-09-24
check_keywords_in_name in 32 papers Classification/imagenet/Swin-Transformer/optimizer.py ran · violated contract Apache-2.0 (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
count_conv2d_layers denoiserep_op/denoiserep/denoise_conv2d.py ran · honoured contract Apache-2.0 (permissive) · 414c3f1f64f991c2 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
count_linear_layers denoiserep_op/denoiserep/denoise_linear.py ran · honoured contract Apache-2.0 (permissive) · 1d9b9dbedc11ca9d · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
count_vit_linear_layers denoiserep_op/denoiserep/denoise_linear.py ran · honoured contract Apache-2.0 (permissive) · 588f3ddb7ae2b2a1 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
create_logger in 172 papers Classification/imagenet/Swin-Transformer/logger.py ran · our draft was wrong Apache-2.0 (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
get_grad_norm in 45 papers Classification/imagenet/Swin-Transformer/utils.py ran · honoured contract Apache-2.0 (permissive) · eec1e7cba51d5e8e · report fixture: signature parameters:list/1/Tensor, norm_type:int/0/int · returned float · level recorded 2026-09-22
load_checkpoint in 277 papers Classification/imagenet/Swin-Transformer/utils.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 59c3a4f0d92e6970 · report fixture: returned float · level recorded 2026-09-24
load_checkpoint in 277 papers Classification/imagenet/Swin-Transformer/utils_simmim.py ran Apache-2.0 (permissive) · 8c60d1a4218dfd1b · report fixture: returned float · level recorded 2026-09-24
pair in 101 papers Classification/cifar-10/vision-transformers-cifar10/models/vit.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 6ba8cee9f5daea41 · report fixture: signature t:int/0/int · returned tuple · level recorded, date not recorded
set_weight_decay in 32 papers Classification/imagenet/Swin-Transformer/optimizer.py ran Apache-2.0 (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
_extract denoiserep_op/denoiserep/denoise_layer.py unverified Apache-2.0 (permissive) · f39904cfad74aa8e · report
fuse_parameters denoiserep_op/denoiserep/denoise_layer.py unverified Apache-2.0 (permissive) · 6233cec4ca021c61 · report
get_config in 203 papers Classification/imagenet/Swin-Transformer/config.py unverified Apache-2.0 (permissive) · b3d06a45875ffab2 · report
get_ploss denoiserep_op/denoiserep/denoise_layer.py unverified Apache-2.0 (permissive) · 366afd054c0b5902 · report
update_config in 54 papers Classification/imagenet/Swin-Transformer/config.py unverified Apache-2.0 (permissive) · 0b3a64a417dd8616 · 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 DenoiseRep (graph method: DenoiseRep). 4 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. DenoiseLayer entry · level 1 · ran · cc79b939ebdd3e56
  2. SinusoidalPositionEmbeddings helper · level 1 · ran · 86b013bf84701f06
  3. _extract helper · level 0 · unverified · f39904cfad74aa8e
  4. _linear_beta_schedule helper · level 1 · ran · honoured contract · 742e7c8b503f4e2f

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="2406.08773") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DenoisingFine-Grained Image ClassificationImage ClassificationImage RetrievalImage SegmentationObject DetectionPerson Re-IdentificationRepresentation LearningSemantic Segmentationimage-classificationmodelobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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