SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.13003 · ICLR · 2021

Robust and Generalizable Visual Representation Learning via Random Convolutions

Colin Raffel, Zhenlin Xu, Deyi Liu, Junlin Yang, Marc Niethammer

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 2 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2007.13003.json · badge: /api/ran/2007.13003.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
wildphoton/RandConv community
Papers with Code archive
2 ran · 1 no recorded run
tourdeml/robust-representation-random-convolutions community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
MultiScaleRandConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
wildphoton/RandConv/lib/networks/rand_conv.py
pointer only (licence: NONE) · get_code("5d97086fdb97d182")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wildphoton/RandConv 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.

RandConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
wildphoton/RandConv/lib/networks/rand_conv.py
pointer only (licence: NONE) · get_code("b49ddd06add45cb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wildphoton/RandConv 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.

randconv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tourdeml/robust-representation-random-convolutions/randconv/randconv.py
code served (permissive licence) · get_code("2d525ad60cbb4382")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
from torch import nn

torch.manual_seed(0)

# Construct a small image tensor: batch_size=2, channels=3, height=4, width=4
image = torch.randn(2, 3, 4, 4)

# K: maximum kernel size for random convolution
K = 3

# mix: whether to blend original and convolved image
mix = True

# p: probability threshold for returning original image
p = 0.5

ARGS = {
    "image": image,
    "K": K,
    "mix": mix,
    "p": p,
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 4) as a later run recorded it
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
RandConvModule Not yet run
unverified (harvested, no recorded run)
wildphoton/RandConv/lib/networks/rand_conv.py
pointer only (licence: NONE) · get_code("5fecd20400ccdedd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wildphoton/RandConv 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. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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 2026-11-21.

Repositories linked to this paper

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

Abstract

While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks can be greatly improved through the use of random convolutions as data augmentation. Random convolutions are approximately shape-preserving and may distort local textures. Intuitively, randomized convolutions create an infinite number of new domains with similar global shapes but random local texture. Therefore, we explore using outputs of multi-scale random convolutions as new images or mixing them with the original images during training. When applying a network trained with our approach to unseen domains, our method consistently improves the performance on domain generalization benchmarks and is scalable to ImageNet. In particular, in the challenging scenario of generalizing to the sketch domain in PACS and to ImageNet-Sketch, our method outperforms state-of-art methods by a large margin. More interestingly, our method can benefit downstream tasks by providing a more robust pretrained visual representation. 1

For agents

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

get_harvested_code_for_paper("2007.13003")
get_code_for_paper("2007.13003")
have("2007.13003")

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

curl https://syntology.ai/api/ran/2007.13003.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.13003.svg)](https://syntology.ai/paper/2007.13003)

Connect an agent — have() is free.