Browse State-of-the-Art › Unsupervised Image Classification
Unsupervised Image Classification
30 papers with code · 7 benchmarks · 6 datasets archive 2025-07-28
Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing 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
7 leaderboard tables shown for this task, 7 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.
Syntology 4 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-20 (1 judged, 0 placed), MNIST (1 judged, 0 placed), CIFAR-10 (1 judged, 0 placed), ImageNet (1 judged, 0 placed), STL-10 (1 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
6 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 45 · with a code link: 30 · where Syntology ran a sample: 12 (11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (12 of 45 tagged: 11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 45 of 45, 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.
-
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets12 Jun 2016 38 repositories listed Syntology 5 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; 4 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.
-
18 Nov 2015 29 repositories listed Syntology 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 9 pointer-only (licence)In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the…
-
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.
-
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.
-
19 Nov 2015 5 repositories listedOur approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an adversarial…
-
15 Nov 2021 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer.
-
14 Oct 2021 2 repositories listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 4 pointer-only (licence)To solve this problem, we propose to maximize the mutual information between the input and the class predictions.
-
19 Mar 2021 2 repositories listedTo guarantee non-degenerate solutions (i. e., solutions where all labels are assigned to the same class) we propose a mathematically motivated variant of the cross-entropy loss that has a uniform prior asserted on the…
-
9 Aug 2020 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 1 pointer-only (licence)Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets.
-
25 May 2020 2 repositories listedFirst, a self-supervised task from representation learning is employed to obtain semantically meaningful features.
-
7 Mar 2018 2 repositories listedCombining Generative Adversarial Networks (GANs) with encoders that learn to encode data points has shown promising results in learning data representations in an unsupervised way.
-
28 Feb 2017 2 repositories listedLearning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation.
-
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.
-
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)In particular, TURTLE matches the average performance of CLIP zero-shot on 26 datasets by employing the same representation space, spanning a wide range of architectures and model sizes.
-
18 Mar 2024 1 repository listedIn this paper, we propose a novel self-supervised learning approach named Iterative Pseudo-supervised Contrastive Learning (IPCL), which utilizes a balanced combination of image augmentations and pseudo-class…
-
6 Feb 2024 1 repository listedCurrent clustering priors for deep latent variable models (DLVMs) require defining the number of clusters a-priori and are susceptible to poor initializations.
-
15 Dec 2023 1 repository listedMultilayer perceptron (MLP) has shown its capability to learn transferable representations in various downstream tasks, such as unsupervised image classification and supervised concept generalization.
-
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)Meanwhile, one-stage methods are developed mainly for representation learning rather than clustering, where various constraints for cluster assignments are designed to avoid collapsing explicitly.
-
21 Sep 2023 1 repository listedDespite its simplicity, HUME outperforms a supervised linear classifier on top of self-supervised representations on the STL-10 dataset by a large margin and achieves comparable performance on the CIFAR-10 dataset.
-
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation21 Mar 2023 1 repository listedWe present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR).
-
22 Sep 2022 1 repository listedCapsule Networks have shown tremendous advancement in the past decade, outperforming the traditional CNNs in various task due to it's equivariant properties.
-
27 Mar 2022 1 repository listedUsing a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones).
-
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)Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination.
-
21 Dec 2020 1 repository listedUnsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results.
-
4 Sep 2020 1 repository listedWe conduct a comparative study on the SOM classification accuracy with unsupervised feature extraction using two different approaches: a machine learning approach with Sparse Convolutional Auto-Encoders using…
-
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)Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data.
-
1 Aug 2020 1 repository listedUnsupervised image classification is a challenging computer vision task.
-
20 Jun 2020 1 repository listedExtensive experiments on ImageNet dataset have been conducted to prove the effectiveness of our method.
-
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)In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and performs clustering directly in image space.
-
2 Jun 2017 1 repository listedIn this paper, we describe the "PixelGAN autoencoder", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code…
-
Contrastive Knowledge Amalgamation for Unsupervised Image Classification27 Jul 2023 0 repositories listed
-
ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision19 Apr 2023 0 repositories listed
-
Minimalistic Unsupervised Learning with the Sparse Manifold Transform30 Sep 2022 0 repositories listed
-
30 Apr 2022 0 repositories listed
-
LatentGAN Autoencoder: Learning Disentangled Latent Distribution5 Apr 2022 0 repositories listed
-
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective1 Dec 2021 0 repositories listed
-
GUIDED MCMC FOR SPARSE BAYESIAN MODELS TO DETECT RARE EVENTS IN IMAGES SANS LABELED DATA29 Sep 2021 0 repositories listed
-
Combining pretrained CNN feature extractors to enhance clustering of complex natural images7 Jan 2021 0 repositories listed
-
AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering1 Jan 2021 0 repositories listed
-
A Pseudo-labelling Auto-Encoder for unsupervised image classification6 Dec 2020 0 repositories listed
-
Unsupervised part representation by Flow Capsules27 Nov 2020 0 repositories listed
-
Unsupervised Image Classification Through Time-Multiplexed Photonic Multi-Layer Spiking Convolutional Neural Network16 Sep 2020 0 repositories listed
-
MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings18 Jul 2020 0 repositories listed
-
Self-supervised classification of dynamic obstacles using the temporal information provided by videos21 Oct 2019 0 repositories listed
-
8 Feb 2018 0 repositories listed
Syntology lines on 13 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