SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.13023 · 2021

Can Vision Transformers Learn without Natural Images?

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 1 has no contract verdict; 7 failures of our instrument; 3 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/2103.13023.json · badge: /api/ran/2103.13023.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
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, 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.

densenet121 Ran
ran; our contract draft was wrong, not the code
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/densenet.py
pointer only (licence: MIT); the stored copy get_code serves, from bennyca/reward, is pointer only (licence: NOASSERTION) · get_code("63a68e9f6bf2f409")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from bennyca/reward, and GitHub could not classify the licence of that repository (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.

densenet169 Ran
ran; our contract draft was wrong, not the code
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/densenet.py
pointer only (licence: MIT); the stored copy get_code serves, from bennyca/reward, is pointer only (licence: NOASSERTION) · get_code("aa68268dc6e7365b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from bennyca/reward, and GitHub could not classify the licence of that repository (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.

densenet201 Ran
ran; our contract draft was wrong, not the code
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/densenet.py
pointer only (licence: MIT); the stored copy get_code serves, from bennyca/reward, is pointer only (licence: NOASSERTION) · get_code("22f2be1e9aacd878")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from bennyca/reward, and GitHub could not classify the licence of that repository (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.

make_layers Ran
ran; our contract draft was wrong, not the code
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/vgg.py
code served (permissive licence) · get_code("ac62432dc5134b0d")
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 Sequential. 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)

# The function takes two parameters: cfg and batch_norm
# cfg should be a list/sequence of either integers (channel counts) or 'M' (maxpool marker)
# batch_norm is a boolean flag

# Using one of the predefined configurations from the module-level cfg dict
cfg_list = [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M']

ARGS = {
    'cfg': cfg_list,
    'batch_norm': False
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
make_layers_features Ran
ran on a synthesized input
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/bn_alexnet.py
code served (permissive licence) · get_code("68d8bd2d7e4d0e88")
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 Sequential. 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)

# Construct cfg parameter - a list of layer specifications
# Each element is either 'M' for MaxPool or a tuple (out_channels, kernel_size, stride, padding)
cfg = [
    (16, 3, 1, 1),  # Conv2d: 3 input channels -> 16 output, kernel=3, stride=1, padding=1
    (32, 3, 1, 1),  # Conv2d: 16 -> 32
    'M',              # MaxPool2d
    (64, 3, 1, 1),  # Conv2d: 32 -> 64
    'M',              # MaxPool2d
]

input_dim = 3  # Input has 3 channels (e.g., RGB image)

bn = True  # Use batch normalization

ARGS = {
    'cfg': cfg,
    'input_dim': input_dim,
    'bn': bn,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
resnet18 Ran
ran; our contract draft was wrong, not the code
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/resnet.py
code served (permissive licence) · get_code("1f8334746ad20d2d")
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 ResNet. 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 ARGS dict with all parameters for resnet18
ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran; our contract draft was wrong, not the code
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/resnet.py
code served (permissive licence) · get_code("e3df93aff5742a22")
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 ResNet. 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)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnext18 Not yet run
unverified (harvested, no recorded run)
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/resnext.py
pointer only (licence: MIT); the stored copy get_code serves, from bennyca/reward, is pointer only (licence: NOASSERTION) · get_code("2030fb453961fb01")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from bennyca/reward, and GitHub could not classify the licence of that repository (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.

resnext34 Not yet run
unverified (harvested, no recorded run)
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/resnext.py
pointer only (licence: MIT); the stored copy get_code serves, from bennyca/reward, is pointer only (licence: NOASSERTION) · get_code("851645a11028145b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from bennyca/reward, and GitHub could not classify the licence of that repository (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.

val Not yet run
unverified (harvested, no recorded run)
hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/finetuning/train_val.py
code served (permissive licence) · get_code("f6a8dbeb6413ff98")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 10 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 1 the same month, 9 later) and 1 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
conv3x3 686 other papers
274 dated earlier, 10 the same month, 396 later, 6 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet18 89 other papers
31 dated earlier, 56 later, 2 same year, order not determinable
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 86 more not named here
make_layers 59 other papers
24 dated earlier, 35 later
1411.4038 (2014-11)
Fully Convolutional Networks for Semantic Segmentation
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1511.05950 (2015-11)
Staleness-aware Async-SGD for Distributed Deep Learning
and 56 more not named here
resnet34 53 other papers
25 dated earlier, 26 later, 2 same year, order not determinable
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 50 more not named here
densenet121 6 other papers
4 dated earlier, 2 later
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1812.00332 (2018-12)
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
and 3 more not named here
densenet169 6 other papers
4 dated earlier, 2 later
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1812.00332 (2018-12)
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
and 3 more not named here
densenet201 6 other papers
4 dated earlier, 2 later
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1812.00332 (2018-12)
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
and 3 more not named here
make_layers_features 2 other papers
2 dated earlier
1608.07017 (2016-08)
Ambient Sound Provides Supervision for Visual Learning
1911.05371 (2019-11)
Self-labelling via simultaneous clustering and representation learning
resnext18 1 other paper
1 later
2311.17232 (2023-11)
ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development
resnext34 1 other paper
1 later
2311.17232 (2023-11)
ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development

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

Can we complete pre-training of Vision Transformers (ViT) without natural images and human-annotated labels? Although a pre-trained ViT seems to heavily rely on a large-scale dataset and human-annotated labels, recent large-scale datasets contain several problems in terms of privacy violations, inadequate fairness protection, and labor-intensive annotation. In the present paper, we pre-train ViT without any image collections and annotation labor. We experimentally verify that our proposed framework partially outperforms sophisticated Self-Supervised Learning (SSL) methods like SimCLRv2 and MoCov2 without using any natural images in the pre-training phase. Moreover, although the ViT pre-trained without natural images produces some different visualizations from ImageNet pre-trained ViT, it can interpret natural image datasets to a large extent. For example, the performance rates on the CIFAR-10 dataset are as follows: our proposal 97.6 vs. SimCLRv2 97.4 vs. ImageNet 98.0.

For agents

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

get_harvested_code_for_paper("2103.13023")
get_code_for_paper("2103.13023")
have("2103.13023")

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

curl https://syntology.ai/api/ran/2103.13023.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.13023.svg)](https://syntology.ai/paper/2103.13023)

Connect an agent — have() is free.