Papers › Breaking the Reclustering Barrier in Centroid-based Deep Clustering

Breaking the Reclustering Barrier in Centroid-based Deep Clustering

4 Nov 2024arXiv:2411.02275archive 2025-07-28

Lukas Miklautz, Timo Klein, Kevin Sidak, Collin Leiber, Thomas Lang, Andrii Shkabrii, Sebastian Tschiatschek, Claudia Plant

This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with periodic reclustering, which we demonstrate to be insufficient to address performance plateaus. We call this phenomenon the "reclustering barrier" and empirically show when the reclustering barrier occurs, what its underlying mechanisms are, and how it is possible to Break the Reclustering Barrier with our algorithm BRB. BRB avoids early over-commitment to initial clusterings and enables continuous adaptation to reinitialized clustering targets while remaining conceptually simple. Applying our algorithm to widely-used centroid-based DC algorithms, we show that (1) BRB consistently improves performance across a wide range of clustering benchmarks, (2) BRB enables training from scratch, and (3) BRB performs competitively against state-of-the-art DC algorithms when combined with a contrastive loss. We release our code and pre-trained models at https://github.com/Probabilistic-and-Interactive-ML/breaking-the-reclustering-barrier .

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="2411.02275")

Code

Syntology Ran 0 of 5 code samples harvested from 1 repository linked to this paper; 5 have no recorded run.

By repository: official repository: 5 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

probabilistic-and-interactive-ml/breaking-the-reclustering-barrier officialmentioned in papermentioned 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

5 samples harvested; 0 ran; 0 honoured the contract we drafted; 5 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.

5unverified

Licence: 0 of the 5 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 probabilistic-and-interactive-ml/breaking-the-reclustering-barrier. “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.

adam_reset_centers_momentum probabilistic-and-interactive-ml/breaking-the-reclustering-barrier/src/deep/brb_reclustering.py official repository unverified BSD-3-Clause (permissive) · 13639c9df329a5ae · report
get_normalize_fn probabilistic-and-interactive-ml/breaking-the-reclustering-barrier/src/datasets/augmentation_dataloader.py official repository unverified BSD-3-Clause (permissive) · 7bc460bf821933f4 · report
get_run_information probabilistic-and-interactive-ml/breaking-the-reclustering-barrier/wandb_downloader.py official repository unverified BSD-3-Clause (permissive) · adc59ade92bb9af0 · report
load_configs_from_files probabilistic-and-interactive-ml/breaking-the-reclustering-barrier/runner.py official repository unverified BSD-3-Clause (permissive) · e432ab3020785a30 · report
update_centers_with_labels probabilistic-and-interactive-ml/breaking-the-reclustering-barrier/src/deep/brb_reclustering.py official repository unverified BSD-3-Clause (permissive) · 8bb08e6cebcb6d20 · report

Tasks

ClusteringDeep ClusteringImage ClusteringUnsupervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 DCN+BRB ARI 0.824 #10 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCN+BRB Accuracy 0.912 #10 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCN+BRB Backbone ResNet-18 #10 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCN+BRB NMI 0.837 #10 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCN+BRB Train set Train #10 of 40 Archive leaderboard report
Image Clustering CIFAR-10 IDEC+BRB ARI 0.818 #11 of 40 Archive leaderboard report
Image Clustering CIFAR-10 IDEC+BRB Accuracy 0.907 #11 of 40 Archive leaderboard report
Image Clustering CIFAR-10 IDEC+BRB Backbone ResNet-18 #11 of 40 Archive leaderboard report
Image Clustering CIFAR-10 IDEC+BRB NMI 0.833 #11 of 40 Archive leaderboard report
Image Clustering CIFAR-10 IDEC+BRB Train set Train #11 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC+BRB ARI 0.812 #12 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC+BRB Accuracy 0.906 #12 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC+BRB Backbone ResNet-18 #12 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC+BRB NMI 0.826 #12 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DEC+BRB Train set Train #12 of 40 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 DCN+BRB ARI 41.15 #4 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 DCN+BRB Accuracy 56.92 #4 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 DCN+BRB NMI 56.76 #4 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 IDEC+BRB ARI 38.81 #7 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 IDEC+BRB Accuracy 55.43 #7 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 IDEC+BRB NMI 54.81 #7 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 DEC+BRB ARI 35.05 #11 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 DEC+BRB Accuracy 50.46 #11 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 DEC+BRB NMI 51.72 #11 of 14 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