Papers › Image Clustering with External Guidance

Image Clustering with External Guidance

18 Oct 2023arXiv:2310.11989archive 2025-07-28

Yunfan Li, Peng Hu, Dezhong Peng, Jiancheng Lv, Jianping Fan, Xi Peng

The core of clustering is incorporating prior knowledge to construct supervision signals. From classic k-means based on data compactness to recent contrastive clustering guided by self-supervision, the evolution of clustering methods intrinsically corresponds to the progression of supervision signals. At present, substantial efforts have been devoted to mining internal supervision signals from data. Nevertheless, the abundant external knowledge such as semantic descriptions, which naturally conduces to clustering, is regrettably overlooked. In this work, we propose leveraging external knowledge as a new supervision signal to guide clustering, even though it seems irrelevant to the given data. To implement and validate our idea, we design an externally guided clustering method (Text-Aided Clustering, TAC), which leverages the textual semantics of WordNet to facilitate image clustering. Specifically, TAC first selects and retrieves WordNet nouns that best distinguish images to enhance the feature discriminability. Then, to improve image clustering performance, TAC collaborates text and image modalities by mutually distilling cross-modal neighborhood information. Experiments demonstrate that TAC achieves state-of-the-art performance on five widely used and three more challenging image clustering benchmarks, including the full ImageNet-1K dataset.

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="2310.11989")

Code

Syntology Ran 4 of 9 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xlearning-scu/2024-icml-tac officialmentioned in paperpytorch 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

9 samples harvested; 4 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.

4ran
5unverified

Licence: 9 of the 9 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 xlearning-scu/2024-icml-tac. “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.

entropy xlearning-scu/2024-icml-tac/loss_utils.py official repository ran fingerprinted no licence file found · pointer only · 9d678f06508155ff · report
get_transforms xlearning-scu/2024-icml-tac/data_utils.py official repository ran no licence file found · pointer only · 3e9f33a6f3e0f2c5 · report
infer xlearning-scu/2024-icml-tac/train_head.py official repository ran no licence file found · pointer only · d37dc82960cdbe7e · report
kmeans xlearning-scu/2024-icml-tac/concat_kmeans.py official repository ran fingerprinted no licence file found · pointer only · aeb283b3541ab5ba · report
calculate_cost_matrix xlearning-scu/2024-icml-tac/eval_utils.py official repository unverified no licence file found · pointer only · f6d031f1affc8b74 · report
consistency_loss xlearning-scu/2024-icml-tac/loss_utils.py official repository unverified no licence file found · pointer only · fd5c16213c636e3f · report
get_cluster_labels_from_indices xlearning-scu/2024-icml-tac/eval_utils.py official repository unverified no licence file found · pointer only · c5807f4f8acc5c0b · report
get_dataloader xlearning-scu/2024-icml-tac/data_utils.py official repository unverified no licence file found · pointer only · 7f816df726bfaadd · report
mine_nearest_neighbors xlearning-scu/2024-icml-tac/data_utils.py official repository unverified no licence file found · pointer only · 635cf1af28d9a524 · report

Tasks

ClusteringImage ClassificationImage Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet-10 TAC ARI 0.983 #2 of 2 Archive leaderboard report
Image Clustering CIFAR-10 TAC ARI 0.831 #8 of 40 Archive leaderboard report
Image Clustering CIFAR-10 TAC Accuracy 0.919 #8 of 40 Archive leaderboard report
Image Clustering CIFAR-10 TAC NMI 0.833 #8 of 40 Archive leaderboard report
Image Clustering CIFAR-20 TAC ARI 0.448 #1 of 1 Archive leaderboard report
Image Clustering CIFAR-20 TAC Accuracy 0.607 #1 of 1 Archive leaderboard report
Image Clustering CIFAR-20 TAC NMI 0.611 #1 of 1 Archive leaderboard report
Image Clustering DTD TAC ARI 34.4 #1 of 2 Archive leaderboard report
Image Clustering DTD TAC Accuracy 50.1 #1 of 2 Archive leaderboard report
Image Clustering DTD TAC NMI 62.1 #1 of 2 Archive leaderboard report
Image Clustering ImageNet-10 TAC Accuracy 0.992 #1 of 18 Archive leaderboard report
Image Clustering ImageNet-10 TAC NMI 0.985 #1 of 18 Archive leaderboard report
Image Clustering STL-10 TAC ARI 0.961 #3 of 29 Archive leaderboard report
Image Clustering STL-10 TAC Accuracy 0.982 #3 of 29 Archive leaderboard report
Image Clustering STL-10 TAC NMI 0.955 #3 of 29 Archive leaderboard report
Image Clustering UCF101 TAC ARI 0.601 #2 of 2 Archive leaderboard report
Image Clustering UCF101 TAC Accuracy 0.687 #2 of 2 Archive leaderboard report
Image Clustering UCF101 TAC NMI 0.823 #2 of 2 Archive leaderboard report
Image Clustering imagenet-1k TAC ARI 0.435 #1 of 1 Archive leaderboard report
Image Clustering imagenet-1k TAC Accuracy 0.582 #1 of 1 Archive leaderboard report
Image Clustering imagenet-1k TAC NMI 0.799 #1 of 1 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