Papers › Unsupervised Deep Embedding for Clustering Analysis

Unsupervised Deep Embedding for Clustering Analysis

19 Nov 2015arXiv:1511.06335archive 2025-07-28

Junyuan Xie, Ross Girshick, Ali Farhadi

Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.

PaperPDFCodeCode Syntology ran

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 25 code samples harvested from 6 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 22 samples from 5 repositories, 10 ran (9 with no instrument failure; 1 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

23 repositories listed; official and paper-mentioned ones first.

piiswrong/dec officialmentioned in papermxnetMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
AdamStein97/Semi-Supervised-BERT-NER mentioned on GitHubtfSyntology: not harvested report
AhmedYounes94/Semi-supervised-BERT-NER mentioned on GitHubtfSyntology: not harvested report
ArronHZG/reid-baseline mentioned on GitHubpytorchSyntology: not harvested report
DIDSR/DomId mentioned on GitHubpytorchMITSyntology: not harvested report
DanielKim0/Gerstein-Lab-Breakseq mentioned on GitHubSyntology: not harvested report
Deepayan137/DeepClustering mentioned on GitHubpytorchSyntology: not harvested report
Derek-Wds/MAD-VAE mentioned on GitHubpytorchMITSyntology: 9 samples, 2 ran (0 instrument-failed) · 7 unverified report
NeptuneProjects/RISCluster mentioned on GitHubpytorchMITSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified report
NeptuneProjects/RISClusterPT mentioned on GitHubpytorchMITSyntology: not harvested report
NeptuneProjects/RISWorkflow mentioned on GitHubMITSyntology: not harvested report
aciobanusebi/deep-clustering mentioned on GitHubtfSyntology: not harvested report
chiqunz/Unsupervised_Models mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
elieJalbout/Clustering-with-Deep-learning mentioned on GitHubSyntology: not harvested report
elitalobo/Hierarchical-RL-Algorithms mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Option-Critic Architecture (arXiv:1609.05140; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
gdec-submission/gdec mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
linqinghong/Deep-Clustering-Paper mentioned on GitHubSyntology: not harvested report
probabilistic-and-interactive-ml/breaking-the-reclustering-barrier mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Breaking the Reclustering Barrier in Centroid-based Deep Clustering (arXiv:2411.02275; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
shyhyawJou/DEC-Pytorch mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
vlukiyanov/pt-dec mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data (arXiv:2505.10704; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
xiaopeng-liao/DEC_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
yamilvindas/gdec mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
yamilvindas/imbalanced_dec_regularization mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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

25 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 12 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 · our draft was wrong
11ran
12unverified

Licence: 3 of the 25 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 6 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

piiswrong/dec official repository 3 samples, 3 ran (0 instrument-failed) · 0 unverified
load_image in 273 papers caffe/python/caffe/io.py ran MIT (permissive) · 03ede571f838f5f3 · report fixture: signature filename:str/0/str, color:bool/0/bool · returned ndarray · level recorded 2026-09-25
oversample caffe/python/caffe/io.py ran MIT (permissive) · c88d90b027f77cc2 · report fixture: signature images:list/1/ndarray, crop_dims:tuple/1/int · returned ndarray · level recorded 2026-09-25
resize_image in 74 papers caffe/python/caffe/io.py ran MIT (permissive) · d47ac8baaac746bc · report fixture: signature im:ndarray/3/float, new_dims:tuple/1/int, interp_order:int/0/int · returned ndarray · level recorded 2026-09-25
Derek-Wds/MAD-VAE community (archive-listed) 9 samples, 2 ran (0 instrument-failed) · 7 unverified
classification_loss in 9 papers utils/loss_function.py ran MIT (permissive) · 7aa6390897fe4c2b · report fixture: signature recon:Tensor/2/float, label:Tensor/1/int, classifier:callable/0/? · returned Tensor · level recorded 2026-09-26
recon_loss_function utils/loss_function.py ran MIT (permissive) · c9e22d972518d2a1 · report fixture: signature recon:Tensor/2/float, target:Tensor/2/float, distribution:Normal/0/?, step:int/0/int, beta:float/0/float · returned tuple · level recorded 2026-09-26
init_models train_classification.py unverified MIT (permissive) · f4153442b81f8700 · report
init_models train_cluster.py unverified MIT (permissive) · 7da1f379244db54a · report
init_models train_identity.py unverified MIT (permissive) · 50ea1de2767835c1 · report
train in 522 papers train_classification.py unverified MIT (permissive) · 870b6390bd4081dc · report
train in 522 papers train_cluster.py unverified MIT (permissive) · 27fe143476938688 · report
train in 522 papers train_combined.py unverified MIT (permissive) · 2df55ac487c883fd · report
train in 522 papers train_identity.py unverified MIT (permissive) · 98418f6d0bad0a09 · report
NeptuneProjects/RISCluster community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
add_to_history RISCluster/utils.py ran MIT (permissive) · d6e817602703c367 · report fixture: signature ll:list/1/list, lv:list/1/int · returned list · level recorded 2026-09-26
batch_eval RISCluster/models.py ran MIT (permissive) · d9430faa6862fe69 · report fixture: signature dataloader:DataLoader/0/?, model:callable/0/?, device:device/0/?, mute:bool/0/bool · returned tuple · level recorded 2026-09-26
batch_training RISCluster/models.py ran MIT (permissive) · c7093f4415d27053 · report fixture: signature model:callable/0/?, dataloader:DataLoader/0/?, optimizer:Adam/0/?, metric:callable/0/?, device:device/0/? · returned tuple · level recorded 2026-09-26
cmap_lifeaquatic RISCluster/plotting.py ran MIT (permissive) · 4f836fac1b516579 · report fixture: signature N:int/0/int · returned list · level recorded 2026-09-26
config_training RISCluster/utils.py ran MIT (permissive) · 38be2f716bcb3572 · report fixture: signature universal:dict/0/?, parameters:dict/0/?, hp:dict/0/? · returned str · level recorded 2026-09-26
file2dt RISCluster/environment.py ran MIT (permissive) · f92fafec77e71af7 · report fixture: signature fname:str/0/str · returned datetime · level recorded 2026-09-26
batch_validation RISCluster/models.py unverified MIT (permissive) · 23d483a57dd94b26 · report
dataset_to_RAM RISCluster/utils.py unverified MIT (permissive) · 8d2a89902994a2db · report
read_ERA5 RISCluster/environment.py unverified MIT (permissive) · 3d2bd71aeaa18f82 · report
read_meteo RISCluster/environment.py unverified MIT (permissive) · 392fae3f6ed46bb4 · report
chiqunz/Unsupervised_Models community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
p_cal DEC/dec_v1.py ran · honoured contract fingerprinted no licence file found · pointer only · 0a30c33474c77768 · report fixture: signature probq:ndarray/2/float · returned ndarray · level recorded 2026-09-22
xiaopeng-liao/DEC_pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
acc in 48 papers
census: 5 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
DEC.py unverified no licence file found · pointer only · df1f11dcac8d2a95 · report
yamilvindas/gdec community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
target_distribution in 16 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/utils/DEC.py ran · our draft was wrong fingerprinted licence not identified · pointer only · e160219c9330b06b · report fixture: signature batch:Tensor/2/float · returned Tensor · level recorded 2026-09-22

Tasks

ClusteringImage ClusteringUnsupervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 DEC ARI 0.161 #37 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC Accuracy 0.301 #37 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC Backbone Custom #37 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC NMI 0.25 #37 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC Train set Train+Test #37 of 40 Archive leaderboard report
Image Clustering CIFAR-100 DEC Accuracy 0.185 #26 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DEC NMI 0.136 #26 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DEC Train Set Train+Test #26 of 30 Archive leaderboard report
Image Clustering CMU-PIE DEC (KL based) Accuracy 0.801 #4 of 4 Archive leaderboard report
Image Clustering CMU-PIE DEC (KL based) NMI 0.924 #4 of 4 Archive leaderboard report
Image Clustering ImageNet-10 DEC Accuracy 0.381 #15 of 18 Archive leaderboard report
Image Clustering ImageNet-10 DEC NMI 0.282 #15 of 18 Archive leaderboard report
Image Clustering Imagenet-dog-15 DEC Accuracy 0.195 #17 of 20 Archive leaderboard report
Image Clustering Imagenet-dog-15 DEC NMI 0.122 #17 of 20 Archive leaderboard report
Image Clustering STL-10 DEC Accuracy 0.359 #26 of 29 Archive leaderboard report
Image Clustering STL-10 DEC NMI 0.276 #26 of 29 Archive leaderboard report
Image Clustering STL-10 DEC Train Split Train+Test #26 of 29 Archive leaderboard report
Image Clustering Tiny-ImageNet DEC Accuracy 0.037 #12 of 14 Archive leaderboard report
Image Clustering Tiny-ImageNet DEC NMI 0.115 #12 of 14 Archive leaderboard report
Image Clustering YouTube Faces DB DEC (KL based) Accuracy 0.371 #4 of 4 Archive leaderboard report
Image Clustering YouTube Faces DB DEC (KL based) NMI 0.446 #4 of 4 Archive leaderboard report
Unsupervised Image Classification SVHN DEC # of clusters (k) 10 #4 of 4 Archive leaderboard report
Unsupervised Image Classification SVHN DEC Acc 11.90 #4 of 4 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.

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