Papers › Joint Unsupervised Learning of Deep Representations and Image Clusters

Joint Unsupervised Learning of Deep Representations and Image Clusters

13 Apr 2016CVPR 2016 6arXiv:1604.03628archive 2025-07-28

Jianwei Yang, Devi Parikh, Dhruv Batra

In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters. In our framework, successive operations in a clustering algorithm are expressed as steps in a recurrent process, stacked on top of representations output by a Convolutional Neural Network (CNN). During training, image clusters and representations are updated jointly: image clustering is conducted in the forward pass, while representation learning in the backward pass. Our key idea behind this framework is that good representations are beneficial to image clustering and clustering results provide supervisory signals to representation learning. By integrating two processes into a single model with a unified weighted triplet loss and optimizing it end-to-end, we can obtain not only more powerful representations, but also more precise image clusters. Extensive experiments show that our method outperforms the state-of-the-art on image clustering across a variety of image datasets. Moreover, the learned representations generalize well when transferred to other tasks.

PaperPDFConference PDFCodeCode 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 1 code sample harvested from 1 repository linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jwyang/joint-unsupervised-learning officialmentioned in papermentioned on GitHubtorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jwyang/JULE-Torch mentioned on GitHubtorchMITSyntology: not harvested report
jwyang/jule.torch mentioned on GitHubtorchMITSyntology: not harvested 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

1 sample harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran

Licence: 0 of the 1 sample 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 jwyang/joint-unsupervised-learning. “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.

jwyang/joint-unsupervised-learning official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
appr_seminmf matlab/approaches/nmf-deep/Deep-Semi-NMF-master/dsnmf/dsnmf.py ran fingerprinted MIT (permissive) · b84d2b5a22f7b8a8 · report fixture: signature M:ndarray/2/float, r:int/0/int · returned tuple · level recorded 2026-09-25

Tasks

ClusteringImage ClusteringRepresentation Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 JULE ARI 0.138 #39 of 40 Archive leaderboard report
Image Clustering CIFAR-10 JULE Accuracy 0.272 #39 of 40 Archive leaderboard report
Image Clustering CIFAR-10 JULE NMI 0.192 #39 of 40 Archive leaderboard report
Image Clustering CIFAR-10 JULE Train set Train+Test #39 of 40 Archive leaderboard report
Image Clustering CIFAR-100 JULE Accuracy 0.137 #29 of 30 Archive leaderboard report
Image Clustering CIFAR-100 JULE NMI 0.103 #29 of 30 Archive leaderboard report
Image Clustering CIFAR-100 JULE Train Set Train+Test #29 of 30 Archive leaderboard report
Image Clustering CMU-PIE JULE-RC NMI 1.000 #1 of 4 Archive leaderboard report
Image Clustering CUB Birds JULE Accuracy 0.044 #4 of 4 Archive leaderboard report
Image Clustering CUB Birds JULE NMI 0.203 #4 of 4 Archive leaderboard report
Image Clustering Coil-20 JULE-RC NMI 1 #1 of 6 Archive leaderboard report
Image Clustering FRGC JULE-RC NMI 0.574 #2 of 3 Archive leaderboard report
Image Clustering ImageNet-10 JULE Accuracy 0.300 #18 of 18 Archive leaderboard report
Image Clustering ImageNet-10 JULE NMI 0.175 #18 of 18 Archive leaderboard report
Image Clustering Imagenet-dog-15 JULE Accuracy 0.138 #20 of 20 Archive leaderboard report
Image Clustering Imagenet-dog-15 JULE NMI 0.054 #20 of 20 Archive leaderboard report
Image Clustering MNIST-full JULE-RC Accuracy 0.964 #13 of 16 Archive leaderboard report
Image Clustering MNIST-full JULE-RC NMI 0.917 #13 of 16 Archive leaderboard report
Image Clustering MNIST-test OURS-RC NMI 0.915 #6 of 11 Archive leaderboard report
Image Clustering STL-10 JULE Accuracy 0.277 #29 of 29 Archive leaderboard report
Image Clustering STL-10 JULE NMI 0.182 #29 of 29 Archive leaderboard report
Image Clustering STL-10 JULE Train Split Train+Test #29 of 29 Archive leaderboard report
Image Clustering Stanford Cars JULE Accuracy 0.046 #5 of 5 Archive leaderboard report
Image Clustering Stanford Cars JULE NMI 0.232 #5 of 5 Archive leaderboard report
Image Clustering Stanford Dogs JULE Accuracy 0.043 #4 of 4 Archive leaderboard report
Image Clustering Stanford Dogs JULE NMI 0.142 #4 of 4 Archive leaderboard report
Image Clustering Tiny-ImageNet JULE Accuracy 0.033 #14 of 14 Archive leaderboard report
Image Clustering Tiny-ImageNet JULE NMI 0.102 #14 of 14 Archive leaderboard report
Image Clustering UMist JULE-RC NMI 0.877 #3 of 4 Archive leaderboard report
Image Clustering USPS JULE-RC NMI 0.913 #9 of 16 Archive leaderboard report
Image Clustering YouTube Faces DB JULE-RC NMI 0.848 #1 of 4 Archive leaderboard report
Image Clustering coil-100 JULE-RC NMI 0.985 #3 of 10 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