SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.04009 · NeurIPS · 2021

Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions

Henry Kvinge, Scott Mahan, Tim Doster

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2106.04009.json · badge: /api/ran/2106.04009.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
g-benton/learning-invariances community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
DiffAug Ran
ran on a synthesized input
g-benton/learning-invariances/augerino/models/aug_modules.py
code served (permissive licence) · get_code("629443866ea9e703")
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 4, 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

class DiffAug(nn.Module):
    """ """

    def __init__(self):
        super().__init__()
        self.Sigma = nn.Parameter(torch.eye(3))
        self.Mu = nn.Parameter(torch.zeros(3))

    def translateRotate(self, x):
        bs, _, w, h = x.size()
        z = torch.randn(bs, 3, device=x.device, dtype=x.dtype) @ self.Sigma + self.Mu
        affineMatrices = torch.zeros(bs, 2, 3, device=x.device, dtype=x.dtype)
        affineMatrices[:, 0, 0] = z[:, 2].cos()
        affineMatrices[:, 0, 1] = -z[:, 2].sin()
        affineMatrices[:, 1, 0] = z[:, 2].sin()
        affineMatrices[:, 1, 1] = z[:, 2].cos()
        affineMatrices[:, :2, 2] = z[:, :2] / (0.5 * w + 0.5 * h)
        affineMatrices = affineMatrices
        flowgrid = torch.nn.functional.affine_grid(affineMatrices, size=x.size(), align_corners=True)
        x_out = torch.nn.functional.grid_sample(x, flowgrid, align_corners=True)
        return x_out

    def forward(self, x):
        return self.translateRotate(x)

    def log_data(self, logger, step, name):
        print(self.Sigma @ self.Sigma.T, self.Mu)

    def __repr__(self):
        return self.__class__.__name__


INIT_ARGS = {}

ARGS = {
    'x': torch.randn(2, 4, 8, 6)
}

if __name__ == '__main__':
    model = DiffAug(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Model: {model}")
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 4, 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)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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.

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

Building invariance to non-meaningful transformations is essential to building efficient and generalizable machine learning models. In practice, the most common way to learn invariance is through data augmentation. There has been recent interest in the development of methods that learn distributions on augmentation transformations from the training data itself. While such approaches are beneficial since they are responsive to the data, they ignore the fact that in many situations the range of transformations to which a model needs to be invariant changes depending on the particular class input belongs to. For example, if a model needs to be able to predict whether an image contains a starfish or a dog, we may want to apply random rotations to starfish images during training (since these do not have a preferred orientation), but we would not want to do this to images of dogs. In this work we introduce a method by which we can learn class conditional distributions on augmentation transformations. We give a number of examples where our methods learn different non-meaningful transformations depending on class and further show how our method can be used as a tool to probe the symmetries intrinsic to a potentially complex dataset.

For agents

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

get_harvested_code_for_paper("2106.04009")
get_code_for_paper("2106.04009")
have("2106.04009")

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

curl https://syntology.ai/api/ran/2106.04009.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.04009.svg)](https://syntology.ai/paper/2106.04009)

Connect an agent — have() is free.