Papers › Deep Transformation-Invariant Clustering

Deep Transformation-Invariant Clustering

19 Jun 2020NeurIPS 2020 12arXiv:2006.11132archive 2025-07-28

Tom Monnier, Thibault Groueix, Mathieu Aubry

Recent advances in image clustering typically focus on learning better deep representations. 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. This learning process naturally fits in the gradient-based training of K-means and Gaussian mixture model, without requiring any additional loss or hyper-parameters. It leads us to two new deep transformation-invariant clustering frameworks, which jointly learn prototypes and transformations. More specifically, we use deep learning modules that enable us to resolve invariance to spatial, color and morphological transformations. Our approach is conceptually simple and comes with several advantages, including the possibility to easily adapt the desired invariance to the task and a strong interpretability of both cluster centers and assignments to clusters. We demonstrate that our novel approach yields competitive and highly promising results on standard image clustering benchmarks. Finally, we showcase its robustness and the advantages of its improved interpretability by visualizing clustering results over real photograph collections.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of Deep Transformation-Invariant Clustering, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Deep Transformation-Invariant Clustering') (how to connect); the free check have('2006.11132') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 6 ran (6 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. 1 of the 6 samples that ran has no recorded date.

monniert/dti-clustering officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified 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

10 samples harvested: 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. “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 · honoured contract
5ran
4unverified

Licence: 0 of the 10 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 monniert/dti-clustering. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

monniert/dti-clustering official repository 10 samples, 6 ran (0 instrument-failed) · 4 unverified
copy_with_noise src/model/tools.py ran fingerprinted MIT (permissive) · 39091286b0f4c42b · report fixture: signature t:Tensor/2/float, noise_scale:float/0/float · returned Tensor · level recorded 2026-09-25
count_parameters in 278 papers src/model/tools.py ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
get_resnet_model src/model/mini_resnet.py ran MIT (permissive) · 672af0454b7920fc · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-25
load_hdf5_file src/dataset/hdf5.py ran MIT (permissive) · 837970845cb82474 · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-25
resnet20 in 42 papers src/model/mini_resnet.py ran MIT (permissive) · a869ef73c638e65a · report fixture: signature in_channels:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-25
resnet32 in 47 papers src/model/mini_resnet.py ran MIT (permissive) · d616bd25aff63b33 · report fixture: signature in_channels:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-25
create_gaussian_weights src/model/tools.py unverified MIT (permissive) · b9217f8a1b76f435 · report
get_resnet_model src/model/resnet.py unverified MIT (permissive) · a25541080f88f65c · report
resnet18 in 432 papers src/model/resnet.py unverified MIT (permissive) · a480f539bff6f901 · report
resnet34 in 148 papers src/model/resnet.py unverified MIT (permissive) · 7907340b312c48da · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

1 assembly on this paper: 0 harvested, 1 generated.

generated Assembly for Deep Transformation-Invariant Clustering (graph method: Deep Transformation-Invariant Clustering), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. dti_gmm_loss entry · level 3 · ran; the contract check could not run · 7b94b3fddba4521682badf30061bd74ff62d07d88dcb09fb2aa149e87f48c2e0

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2006.11132") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClusteringImage ClusteringUnsupervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering Fashion-MNIST DTI-Clustering Accuracy 0.612 #10 of 13 Archive leaderboard report
Image Clustering Fashion-MNIST DTI-Clustering NMI 0.637 #10 of 13 Archive leaderboard report
Image Clustering MNIST-full DTI-Clustering Accuracy 0.979 #7 of 16 Archive leaderboard report
Image Clustering MNIST-full DTI-Clustering NMI 0.942 #7 of 16 Archive leaderboard report
Image Clustering MNIST-test DTI-Clustering Accuracy 0.978 #2 of 11 Archive leaderboard report
Image Clustering MNIST-test DTI-Clustering NMI 0.947 #2 of 11 Archive leaderboard report
Image Clustering USPS DTI-Clustering Accuracy 0.864 #13 of 16 Archive leaderboard report
Image Clustering USPS DTI-Clustering NMI 0.882 #13 of 16 Archive leaderboard report
Unsupervised Image Classification MNIST DTI-Clustering Accuracy 97.3 #4 of 10 Archive leaderboard report
Unsupervised Image Classification SVHN DTI-Clustering # of clusters (k) 10 #2 of 4 Archive leaderboard report
Unsupervised Image Classification SVHN DTI-Clustering Acc 57.4 #2 of 4 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.

Methods

Interpretability

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