SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.02693 · 2019

StampNet: unsupervised multi-class object discovery

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 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; 1 failure of our instrument; 1 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/1902.02693.json · badge: /api/ran/1902.02693.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
crowdflowTUe/stampnet community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_cost_matrix Ran
ran; our contract draft was wrong, not the code
crowdflowTUe/stampnet/utils/extra_util.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from XiaojianDing/2025-NeurIPS-HSACC, is pointer only (licence: NONE) · get_code("f6d031f1affc8b74")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from XiaojianDing/2025-NeurIPS-HSACC, and GitHub detected no licence in that repository 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_cluttered_mnist Ran
ran on a synthesized input
crowdflowTUe/stampnet/utils/img_gen.py
code served (permissive licence) · get_code("d4722b852eb8617f")
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 tuple. 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 numpy as np
import tempfile
import os

# Create a temporary npz file with the required structure
temp_dir = tempfile.mkdtemp()
data_path = os.path.join(temp_dir, "cluttered_mnist.npz")

# Create minimal valid data arrays
x_train = np.random.randint(0, 256, (2, 28, 28), dtype=np.uint8)
y_train = np.array([0, 1], dtype=np.int64)
x_train_coords = np.random.randn(2, 4).astype(np.float32)

x_test = np.random.randint(0, 256, (2, 28, 28), dtype=np.uint8)
y_test = np.array([1, 0], dtype=np.int64)
x_test_coords = np.random.randn(2, 4).astype(np.float32)

# Save to npz file
np.savez(
    data_path,
    x_train=x_train,
    y_train=y_train,
    x_train_coords=x_train_coords,
    x_test=x_test,
    y_test=y_test,
    x_test_coords=x_test_coords
)

ARGS = {
    "data_path": data_path,
    "test_only": False,
    "random_seed": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
get_scale Ran
ran on a synthesized input
crowdflowTUe/stampnet/utils/extra_util.py
code served (permissive licence) · get_code("b482d03e6f8ffec4")
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 float64, ndim 0, 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 numpy as np

# Create a small sample dataset for x
# The function will reshape it to (batch_size, flattened_features)
# Using shape (10, 4) to have 10 points with 4 features each
x = np.random.randn(10, 4).astype(np.float32)

batch_size = 3
n_nbrs = 2

ARGS = {
    "x": x,
    "batch_size": batch_size,
    "n_nbrs": n_nbrs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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: none by the harness; any seed is in the setup block
make_layer_list Ran
ran on a synthesized input
crowdflowTUe/stampnet/utils/extra_util.py
code served (permissive licence) · get_code("a3f6d9141e555686")
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 list, ndim 1, 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 as nn

torch.manual_seed(0)

ARGS = {
    'arch': [
        {
            'type': 'Dense',
            'size': 64,
            'activation': 'relu'
        },
        {
            'type': 'Dense',
            'size': 32,
            'activation': 'relu'
        },
        {
            'type': 'Flatten'
        },
        {
            'type': 'Dense',
            'size': 10,
            'activation': 'softmax'
        }
    ],
    'network_type': 'siamese',
    'reg': 0.001,
    'dropout': 0.5
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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: none by the harness; any seed is in the setup block
get_cluttered_mnist Not yet run
unverified (harvested, no recorded run)
crowdflowTUe/stampnet/utils/img_gen_debug.py
code served (permissive licence) · get_code("7edb402f71af2925")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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.

FunctionAlso present inEarliest-datedOthers named
calculate_cost_matrix 9 other papers
9 later
2009.09687 (2020-09)
Contrastive Clustering
2110.07402 (2021-10)
Self-Supervised Learning by Estimating Twin Class Distributions
2301.11045 (2023-01)
Incomplete Multi-view Clustering via Prototype-based Imputation
and 6 more not named here
get_scale 2 other papers
2 later
1905.12724 (2019-05)
Variational Diffusion Autoencoders with Random Walk Sampling
aaai_25868 (2023 (year only))
TC-DWA: Text Clustering with Dual Word-Level Augmentation
make_layer_list 2 other papers
2 later
1905.12724 (2019-05)
Variational Diffusion Autoencoders with Random Walk Sampling
aaai_25868 (2023 (year only))
TC-DWA: Text Clustering with Dual Word-Level Augmentation

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

Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than image clustering as the size and the location of the objects are not known: this adds additional degrees of freedom and increases the problem complexity. In this work, we propose StampNet, a novel autoencoding neural network that localizes shapes (objects) over a simple background in images and categorizes them simultaneously. StampNet consists of a discrete latent space that is used to categorize objects and to determine the location of the objects. The object categories are formed during the training, resulting in the discovery of a fixed set of objects. We present a set of experiments that demonstrate that StampNet is able to localize and cluster multiple overlapping shapes with varying complexity including the digits from the MNIST dataset. We also present an application of StampNet in the localization of pedestrians in overhead depth-maps.

For agents

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

get_harvested_code_for_paper("1902.02693")
get_code_for_paper("1902.02693")
have("1902.02693")

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

curl https://syntology.ai/api/ran/1902.02693.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.02693.svg)](https://syntology.ai/paper/1902.02693)

Connect an agent — have() is free.