Papers › Deep Online Probability Aggregation Clustering

Deep Online Probability Aggregation Clustering

7 Jul 2024arXiv:2407.05246archive 2025-07-28

Yuxuan Yan, Na Lu, Ruofan Yan

Combining machine clustering with deep models has shown remarkable superiority in deep clustering. It modifies the data processing pipeline into two alternating phases: feature clustering and model training. However, such alternating schedule may lead to instability and computational burden issues. We propose a centerless clustering algorithm called Probability Aggregation Clustering (PAC) to proactively adapt deep learning technologies, enabling easy deployment in online deep clustering. PAC circumvents the cluster center and aligns the probability space and distribution space by formulating clustering as an optimization problem with a novel objective function. Based on the computation mechanism of the PAC, we propose a general online probability aggregation module to perform stable and flexible feature clustering over mini-batch data and further construct a deep visual clustering framework deep PAC (DPAC). Extensive experiments demonstrate that PAC has superior clustering robustness and performance and DPAC remarkably outperforms the state-of-the-art deep clustering 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 10 code samples harvested from 1 repository linked to this paper: 7 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; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

aomandechenai/deep-probability-aggregation-clustering officialmentioned in paperpytorchSyntology: 10 samples, 7 ran (5 instrument-failed) · 3 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

10 samples harvested: 7 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; 5 where Syntology's instrument failed) · 3 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 · honoured contract
1ran · violated contract
5ran · our draft was wrong
3unverified

Licence: 10 of the 10 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 aomandechenai/deep-probability-aggregation-clustering. “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.

aomandechenai/deep-probability-aggregation-clustering official repository 10 samples, 7 ran (5 instrument-failed) · 3 unverified
calculate_cost_matrix in 10 papers PAC_DPAC_program/evaluation.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f6d031f1affc8b74 · report fixture: signature C:ndarray/2/float, n_clusters:int/0/int · returned ndarray · level recorded 2026-09-25
get_cluster_labels_from_indices in 8 papers PAC_DPAC_program/evaluation.py ran · honoured contract no licence file found · pointer only · c5807f4f8acc5c0b · report fixture: signature indices:list/1/tuple · returned ndarray · level recorded 2026-09-25
get_resnet in 13 papers PAC_DPAC_program/models/resnet.py ran · our draft was wrong no licence file found · pointer only · a3799b1622a4261a · report fixture: signature name:str/0/str · returned ResNet · level recorded 2026-09-24
get_resnet_cifar PAC_DPAC_program/models/resnet_cifar.py ran · our draft was wrong no licence file found · pointer only · a394b6a4fad5a4e5 · report fixture: signature name:str/0/str · returned ResNet · level recorded 2026-09-24
get_resnet_stl PAC_DPAC_program/models/resnet_stl.py ran · our draft was wrong no licence file found · pointer only · 97f23de7840fbb7d · report fixture: signature name:str/0/str · returned ResNet · level recorded 2026-09-24
pac_loss PAC_DPAC_program/clustering_step.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8ed3862e4beebd1e · report fixture: signature p:Tensor/2/float, f:Tensor/2/float · returned Tensor · level recorded 2026-09-24
pairwise_cosine in 6 papers PAC_DPAC_program/probability_aggregation_clustering.py ran · violated contract fingerprinted no licence file found · pointer only · 9055a311efaae473 · report fixture: signature x1:ndarray/2/float, x2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_shuffle_idx PAC_DPAC_program/probability_aggregation_clustering.py unverified no licence file found · pointer only · 3a093ae871761352 · report
pairwise_euclidean PAC_DPAC_program/probability_aggregation_clustering.py unverified no licence file found · pointer only · 5f712aed23048925 · report
train_model in 103 papers PAC_DPAC_program/clustering_step.py unverified no licence file found · pointer only · 562db12f15d6f0f9 · report

Tasks

ClusteringDeep ClusteringImage ClassificationImage Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 DPAC ARI 0.866 #5 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DPAC Accuracy 0.934 #5 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DPAC Backbone ResNet-34 #5 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DPAC NMI 0.87 #5 of 40 Archive leaderboard report
Image Clustering CIFAR-100 DPAC ARI 0.393 #8 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DPAC Accuracy 0.555 #8 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DPAC Backbone ResNet-34 #8 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DPAC NMI 0.542 #8 of 30 Archive leaderboard report
Image Clustering ImageNet-10 DPAC ARI 0.935 #3 of 18 Archive leaderboard report
Image Clustering ImageNet-10 DPAC Accuracy 0.97 #3 of 18 Archive leaderboard report
Image Clustering ImageNet-10 DPAC Backbone ResNet-34 #3 of 18 Archive leaderboard report
Image Clustering ImageNet-10 DPAC NMI 0.925 #3 of 18 Archive leaderboard report
Image Clustering Imagenet-dog-15 DPAC ARI 0.598 #6 of 20 Archive leaderboard report
Image Clustering Imagenet-dog-15 DPAC Accuracy 0.726 #6 of 20 Archive leaderboard report
Image Clustering Imagenet-dog-15 DPAC Backbone ResNet-34 #6 of 20 Archive leaderboard report
Image Clustering Imagenet-dog-15 DPAC NMI 0.667 #6 of 20 Archive leaderboard report
Image Clustering STL-10 DPAC ARI 0.861 #5 of 29 Archive leaderboard report
Image Clustering STL-10 DPAC Accuracy 0.934 #5 of 29 Archive leaderboard report
Image Clustering STL-10 DPAC Backbone ResNet-34 #5 of 29 Archive leaderboard report
Image Clustering STL-10 DPAC NMI 0.863 #5 of 29 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

Contrastive Learning

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