SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.05520 · 2018

Deep Clustering for Unsupervised Learning of Visual Features

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1807.05520.json · badge: /api/ran/1807.05520.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
bdy9527/SDCN community
Papers with Code archive
2 ran · 1 no recorded run
betashort/DeepClusterings community
Papers with Code archive
2 ran · 0 no recorded run
hsfzxjy/swavx community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
AE Ran
ran on a synthesized input · constructed an object; no result was computed
bdy9527/SDCN/sdcn.py
code served (permissive licence) · get_code("c9adc6036aa45d3e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, AE: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define the arguments for the AE class
ARGS = {
    'n_enc_1': 32,
    'n_enc_2': 16,
    'n_enc_3': 8,
    'n_dec_1': 8,
    'n_dec_2': 16,
    'n_dec_3': 32,
    'n_input': 64,
    'n_z': 4,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type AE — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a AE output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
GNNLayer Ran
ran on a synthesized input
bdy9527/SDCN/sdcn.py
code served (permissive licence) · get_code("5c5c46d837a22ed0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F
from torch.nn.parameter import Parameter
from torch.nn.modules.module import Module

class GNNLayer(Module):

    def __init__(self, in_features, out_features):
        super(GNNLayer, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.weight = Parameter(torch.FloatTensor(in_features, out_features))
        torch.nn.init.xavier_uniform_(self.weight)

    def forward(self, features, adj, active=True):
        support = torch.mm(features, self.weight)
        output = torch.spmm(adj, support)
        if active:
            output = F.relu(output)
        return output


INIT_ARGS = {
    'in_features': 4,
    'out_features': 3,
}

num_nodes = 2
in_features = 4
out_features = 3

features = torch.randn(num_nodes, in_features)
indices = torch.LongTensor([[0, 1], [1, 0]])
values = torch.FloatTensor([1.0, 1.0])
adj = torch.sparse_coo_tensor(indices, values, (num_nodes, num_nodes))

ARGS = {
    'features': features,
    'adj': adj,
    'active': True,
}

if __name__ == '__main__':
    layer = GNNLayer(**INIT_ARGS)
    output = layer(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output:\n{output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ReassignedDataset Ran
ran on a synthesized input · constructed an object; no result was computed
betashort/DeepClusterings/DeepClustering/deepcluster.py
pointer only (licence: NONE) · get_code("2ec706e9bf55a6df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, betashort/DeepClusterings when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cluster_assign Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
betashort/DeepClusterings/DeepClustering/deepcluster.py
pointer only (licence: NONE) · get_code("50c8238f31118570")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, betashort/DeepClusterings when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_indices_sparse Ran
ran; our contract draft was wrong, not the code
hsfzxjy/swavx/main_deepclusterv2.py
pointer only (licence: NOASSERTION) · get_code("c2abbf3e8913b375")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, hsfzxjy/swavx (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SDCN Not yet run
unverified (harvested, no recorded run)
bdy9527/SDCN/sdcn.py
code served (permissive licence) · get_code("4aee3d437cd88960")
How it ran

no invocation recorded.

cluster_memory Not yet run
unverified (harvested, no recorded run)
hsfzxjy/swavx/main_deepclusterv2.py
pointer only (licence: NOASSERTION) · get_code("7a53b1371c3b1e7b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, hsfzxjy/swavx (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on large scale datasets. 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. DeepCluster iteratively groups the features with a standard clustering algorithm, kmeans, and uses the subsequent assignments as supervision to update the weights of the network. We apply DeepCluster to the unsupervised training of convolutional neural networks on large datasets like ImageNet and YFCC100M. The resulting model outperforms the current state of the art by a significant margin on all the standard benchmarks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1807.05520")
get_code_for_paper("1807.05520")
have("1807.05520")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1807.05520.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1807.05520.svg)](https://syntology.ai/paper/1807.05520)

Connect an agent — have() is free.