Browse State-of-the-Art › Image Clustering
Image Clustering
118 papers with code · 55 benchmarks · 44 datasets archive 2025-07-28
Models that partition the dataset into semantically meaningful clusters without having access to the ground truth labels.
Image credit: ImageNet clustering results of SCAN: Learning to Classify Images without Labels (ECCV 2020)
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
55 leaderboard tables shown for this task, 55 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 55 until expanded.
Syntology 11 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): CIFAR-10 (6 judged, 0 placed), CIFAR-100 (4 judged, 0 placed), STL-10 (2 judged, 0 placed), ImageNet-10 (2 judged, 0 placed), MNIST-full (2 judged, 0 placed), USPS (1 judged, 0 placed), Tiny-ImageNet (1 judged, 0 placed), ImageNet (1 judged, 0 placed), HAR (3 judged, 0 placed), MNIST (2 judged, 0 placed), DTD (2 judged, 0 placed), LetterA-J (1 judged, 0 placed), pendigits (1 judged, 0 placed), CIFAR-20 (1 judged, 0 placed), imagenet-1k (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
44 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 44 until expanded.
Subtasks archive 2025-07-28
4 subtasks in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 236 · with a code link: 118 · where Syntology ran a sample: 26 (20 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (26 of 236 tagged: 20 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 236, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
19 Nov 2015 258 repositories listed Syntology 128 ran (of which 61 constructed an object rather than computing a result; 111 with no instrument failure: 3 honoured, 0 violated, 108 with no contract checked; 17 where Syntology's instrument failed) · 91 unverified (of 219 harvested samples) · 111 pointer-only (licence)In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications.
-
20 Dec 2013 144 repositories listed Syntology 140 ran (of which 52 constructed an object rather than computing a result; 120 with no instrument failure: 4 honoured, 2 violated, 114 with no contract checked; 20 where Syntology's instrument failed) · 59 unverified (of 199 harvested samples) · 103 pointer-only (licence)First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods.
-
19 Nov 2015 23 repositories listed Syntology official (archive's flag): 3 ran · 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 (of 25 harvested samples) · 3 pointer-only (licence)Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms.
-
15 Jul 2018 9 repositories listed Syntology community repositories only · 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 4 pointer-only (licence)In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features.
-
17 Jul 2018 6 repositories listed Syntology official (archive's flag): 2 ran · 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (of 18 harvested samples)The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.
-
13 Nov 2019 5 repositories listed Syntology official (archive's flag): 13 ran · 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified (of 18 harvested samples) · 6 pointer-only (licence)Combining clustering and representation learning is one of the most promising approaches for unsupervised learning of deep neural networks.
-
16 Aug 2019 5 repositories listed Syntology official (archive's flag): 2 ran · 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) · 2 unverified (of 4 harvested samples) · 2 pointer-only (licence)We study a number of local and global manifold learning methods on both the raw data and autoencoded embedding, concluding that UMAP in our framework is best able to find the most clusterable manifold in the embedding…
-
5 Mar 2012 4 repositories listedIn this paper, we propose and study an algorithm, called Sparse Subspace Clustering (SSC), to cluster data points that lie in a union of low-dimensional subspaces.
-
3 Jul 2021 3 repositories listedOur hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
-
10 Jun 2019 3 repositories listedThe algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data…
-
8 Sep 2017 3 repositories listedWe present a novel deep neural network architecture for unsupervised subspace clustering.
-
13 Apr 2016 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters.
-
15 Feb 2024 2 repositories listed Syntology official (archive's flag): 1 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models.
-
21 Oct 2022 2 repositories listedSpecifically, we find that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster…
-
21 Dec 2021 2 repositories listedWe define a distance function between images, each of which is represented as a bag of embeddings, by the Euclidean distance between weighted averaged embeddings.
-
21 Sep 2020 2 repositories listed Syntology official (archive's flag): 5 ran · 7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 3 pointer-only (licence)In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning.
-
15 Jun 2020 2 repositories listedThe dissimilarity mixture autoencoder (DMAE) is a neural network model for feature-based clustering that incorporates a flexible dissimilarity function and can be integrated into any kind of deep learning architecture.
-
15 Jun 2020 2 repositories listed Syntology official (archive's flag): 1 ran · 1 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; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction (MCR²), an information-theoretic measure that…
-
25 May 2020 2 repositories listedFirst, a self-supervised task from representation learning is employed to obtain semantically meaningful features.
-
20 Jan 2020 2 repositories listedIn this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to both reduced clustering performance, and a significant amount of OFM between the…
-
6 Jul 2017 2 repositories listedThis paper aims at providing insight on the transferability of deep CNN features to unsupervised problems.
-
23 Mar 2017 2 repositories listedTraditional image clustering methods take a two-step approach, feature learning and clustering, sequentially.
-
5 Jul 2015 2 repositories listedSubspace clustering methods based on ℓ₁, ℓ₂ or nuclear norm regularization have become very popular due to their simplicity, theoretical guarantees and empirical success.
-
25 Aug 2012 2 repositories listedWe explore the different roles of two fundamental concepts in graph theory, indegree and outdegree, in the context of clustering.
-
11 Jun 2025 1 repository listedHyperspectral image (HSI) clustering assigns similar pixels to the same class without any annotations, which is an important yet challenging task.
-
1 Feb 2025 1 repository listedWe propose a novel approach for optimizing the graph ratio-cut by modeling the binary assignments as random variables.
-
25 Dec 2024 1 repository listedIn the era of pre-trained models, image clustering task is usually addressed by two relevant stages: a) to produce features from pre-trained vision models; and b) to find clusters from the pre-trained features.
-
2 Dec 2024 1 repository listedFor broad visual frames, DINOv2 is a suitable embedding space, while ConvNeXt V2 returns a larger number of clusters which contain fine-grain differences, i. e. speech and protest.
-
4 Nov 2024 1 repository listed Syntology official (archive's flag): 2 ran · 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 (of 5 harvested samples)This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains.
-
6 Sep 2024 1 repository listedHowever, there is a gap between visual representation learning and textual semantic learning, and how to properly utilize the representation of two different modalities for clustering is still a big challenge.
-
3 Sep 2024 1 repository listed
-
4 Aug 2024 1 repository listed
-
7 Jul 2024 1 repository listed Syntology official (archive's flag): 7 ran · 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 (of 10 harvested samples) · 10 pointer-only (licence)
-
25 Jun 2024 1 repository listed
-
11 Jun 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
13 May 2024 1 repository listed
-
18 Mar 2024 1 repository listed
-
1 Mar 2024 1 repository listed
-
6 Feb 2024 1 repository listed
-
5 Feb 2024 1 repository listed
-
24 Jan 2024 1 repository listed
-
25 Dec 2023 1 repository listed
-
24 Dec 2023 1 repository listed
-
24 Nov 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
27 Oct 2023 1 repository listed Syntology official (archive's flag): 2 ran · 3 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; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
18 Oct 2023 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples) · 9 pointer-only (licence)
-
21 Sep 2023 1 repository listed
-
8 Jun 2023 1 repository listed
-
20 Apr 2023 1 repository listed
-
31 Mar 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 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; 4 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
3 Mar 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
14 Nov 2022 1 repository listed
-
26 Sep 2022 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)
-
26 Sep 2022 1 repository listed
-
21 Sep 2022 1 repository listed
-
17 Sep 2022 1 repository listed
-
14 Jul 2022 1 repository listed
-
26 Jun 2022 1 repository listed
-
26 May 2022 1 repository listed
-
1 May 2022 1 repository listed
-
18 Mar 2022 1 repository listed
-
1 Mar 2022 1 repository listed
-
1 Feb 2022 1 repository listed
-
31 Jan 2022 1 repository listed
-
23 Nov 2021 1 repository listed
-
15 Nov 2021 1 repository listed
-
27 Aug 2021 1 repository listed
-
23 Aug 2021 1 repository listed
-
23 Jul 2021 1 repository listed
-
22 Jul 2021 1 repository listed
-
29 Jun 2021 1 repository listed
-
31 May 2021 1 repository listed
-
24 May 2021 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
5 May 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result (of 3 harvested samples) · 3 pointer-only (licence)
-
4 May 2021 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
17 Mar 2021 1 repository listed
-
12 Mar 2021 1 repository listed
-
10 Feb 2021 1 repository listed
-
21 Dec 2020 1 repository listed
-
30 Nov 2020 1 repository listed
-
23 Nov 2020 1 repository listed
-
8 Nov 2020 1 repository listed
-
24 Aug 2020 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples)
-
1 Aug 2020 1 repository listed
-
20 Jul 2020 1 repository listed
-
20 Jun 2020 1 repository listed
-
19 Jun 2020 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples)
-
17 Jun 2020 1 repository listed
-
11 Jun 2020 1 repository listed
-
5 Jun 2020 1 repository listed
-
10 Apr 2020 1 repository listed
-
27 Feb 2020 1 repository listed
-
13 Feb 2020 1 repository listed
-
5 Dec 2019 1 repository listed
-
23 Aug 2019 1 repository listed
-
5 Jul 2019 1 repository listed
-
15 Apr 2019 1 repository listed
-
7 Feb 2019 1 repository listed Syntology 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 1 pointer-only (licence)
Syntology lines on 26 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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