SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.11102 · 2020

On Feature Normalization and Data Augmentation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 14 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; 5 failures of our instrument; 8 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/2002.11102.json · badge: /api/ran/2002.11102.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
Boyiliee/MoEx canonical (classifier label)
classifier basis: census
6 ran · 8 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran; our contract draft was wrong, not the code
Boyiliee/MoEx/ModelNet/pointnet2_classification_moex.py
code served (permissive licence) · get_code("b8bc16d9fb9a63e3")
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 MLP function takes:
# 1. channels: a list/sequence of integers representing layer dimensions
# 2. batch_norm: a boolean flag for whether to use batch normalization

# Looking at the function body:
# - channels is indexed with channels[i-1] and channels[i] in a loop from 1 to len(channels)
# - This means channels needs at least 2 elements
# - Each element is passed to Lin() which expects integer dimensions
# - batch_norm is used in a boolean condition to include BN layers

# Construct valid arguments:
channels = [4, 8, 6, 3]  # Input dim 4 -> hidden 8 -> hidden 6 -> output 3

ARGS = {
    "channels": channels,
    "batch_norm": True
}
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 2 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
Boyiliee/MoEx/ImageNet/moex_resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
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) and returned Conv2d. 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 conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
Boyiliee/MoEx/ImageNet/moex_resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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) and returned Conv2d. 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 = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
Boyiliee/MoEx/CIFAR/pyramidnet_moex.py
pointer only (licence: BSD-3-Clause); 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 (BSD-3-Clause), 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.

fast_collate Ran
ran; our contract draft was wrong, not the code
Boyiliee/MoEx/ImageNet/main_moex.py
code served (permissive licence) · get_code("1795ac057ca3e793")
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 torch
import numpy as np
from PIL import Image

torch.manual_seed(0)

# Create small PIL images with size attribute (width, height)
img1 = Image.new('RGB', (4, 3))
img2 = Image.new('RGB', (4, 3))

# Create batch items: (image, target_label)
batch = [
    (img1, 0),
    (img2, 1)
]

ARGS = {
    'batch': batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — 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
moex Ran
ran on a synthesized input
Boyiliee/MoEx/ModelNet/pointnet2_classification_moex.py
code served (permissive licence) · get_code("22a17ae488f5df43")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Build minimal arguments for moex function
B = 2  # batch size
T = 3  # time steps
C = 4  # channel dimension

# x: shape (B*T, C) - flattened feature tensor
x = torch.randn(B * T, C)

# pos: position tensor (not used in function body, but required parameter)
pos = torch.randn(B * T, 2)

# batch: batch assignment tensor of size B*T
batch = torch.repeat_interleave(torch.arange(B), T)

# swap_index: indices for swapping, shape (B,)
# These are indices into the batch dimension
swap_index = torch.tensor([1, 0])

ARGS = {
    'x': x,
    'pos': pos,
    'batch': batch,
    'swap_index': swap_index,
    'norm_type': 'pono',
    'epsilon': 1e-05
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — 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
moex Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/ImageNet/moex_resnet.py
code served (permissive licence) · get_code("5f4567b0710fa9b5")
How it ran

no invocation recorded.

rand_bbox Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/CIFAR/train_moex.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from deeplearning-wisc/dream-ood, is pointer only (licence: NOASSERTION) · get_code("d34a085d71b8f4b5")
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 deeplearning-wisc/dream-ood, 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.

train Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/ImageNet/main_moex.py
code served (permissive licence) · get_code("750382b7eb3ffbc5")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/ImageNet/main_moex_cutmix.py
code served (permissive licence) · get_code("78af1ef51a7861c5")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/ModelNet/pointnet2_classification_moex.py
code served (permissive licence) · get_code("c92643c0c22f35c2")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/CIFAR/train_moex.py
code served (permissive licence) · get_code("0af00a0c1d3cde30")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/ImageNet/main_moex.py
code served (permissive licence) · get_code("d3bd4edad0609d00")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
Boyiliee/MoEx/CIFAR/train_moex.py
code served (permissive licence) · get_code("4f145b01a69b877b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 6 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.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
187 dated earlier, 9 the same month, 489 later, 1 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
conv1x1 431 other papers
57 dated earlier, 1 the same month, 372 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
28 dated earlier, 1 the same month, 282 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
rand_bbox 13 other papers
1 dated earlier, 12 later
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
2003.05438 (2020-03)
Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning
2007.00992 (2020-07)
Rethinking Channel Dimensions for Efficient Model Design
and 10 more not named here
MLP 3 other papers
1 dated earlier, 2 later
1612.07659 (2016-12)
Structured Sequence Modeling with Graph Convolutional Recurrent Networks
2004.01301 (2020-04)
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
2010.05501 (2020-10)
BiPointNet: Binary Neural Network for Point Clouds
fast_collate 2 other papers
2 dated earlier
1904.05049 (2019-04)
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
1908.09699 (2019-08)
Gated Convolutional Networks with Hybrid Connectivity for Image Classification
moex 1 other paper
1 later
136850478 (2022 (year only))
Unbiased Manifold Augmentation for Coarse Class Subdivision

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

The moments (a.k.a., mean and standard deviation) of latent features are often removed as noise when training image recognition models, to increase stability and reduce training time. However, in the field of image generation, the moments play a much more central role. Studies have shown that the moments extracted from instance normalization and positional normalization can roughly capture style and shape information of an image. Instead of being discarded, these moments are instrumental to the generation process. In this paper we propose Moment Exchange, an implicit data augmentation method that encourages the model to utilize the moment information also for recognition models. Specifically, we replace the moments of the learned features of one training image by those of another, and also interpolate the target labels -- forcing the model to extract training signal from the moments in addition to the normalized features. As our approach is fast, operates entirely in feature space, and mixes different signals than prior methods, one can effectively combine it with existing augmentation approaches. We demonstrate its efficacy across several recognition benchmark data sets where it improves the generalization capability of highly competitive baseline networks with remarkable consistency.

For agents

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

get_harvested_code_for_paper("2002.11102")
get_code_for_paper("2002.11102")
have("2002.11102")

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

curl https://syntology.ai/api/ran/2002.11102.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.11102.svg)](https://syntology.ai/paper/2002.11102)

Connect an agent — have() is free.