SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.03647 · ICCV · 2021

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Qian Li, Errui Ding, Xin Li, Fu Li, Songhua Liu, Meiling Wang, Dongliang He, Tianwei Lin, Zhengxing Sun

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 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; 2 failures of our instrument; 0 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/2108.03647.json · badge: /api/ran/2108.03647.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
gaetano-signorelli/Attention-Style-Transfer community
Papers with Code archive
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
huage001/adaattn marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
AdaAttN Ran
ran on a synthesized input · constructed an object; no result was computed
huage001/adaattn/models/networks.py
code served (permissive licence) · get_code("4f2e5459ea18fa72")
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 an instance of its own class, AdaAttN: the run constructed the object and did not call it, so no result was computed. 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)

# Create small test tensors
# Batch size 2, channels 4, height 3, width 3
batch_size = 2
channels = 4
height = 3
width = 3

content = torch.randn(batch_size, channels, height, width)
style = torch.randn(batch_size, channels, height, width)
content_key = torch.randn(batch_size, channels, height, width)
style_key = torch.randn(batch_size, channels, height, width)

ARGS = {
    'in_planes': channels,
    'max_sample': 256 * 256,
    'key_planes': channels,
}
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 AdaAttN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a AdaAttN 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
AdaptiveAttentionLayer Ran
ran on a synthesized input · constructed an object; no result was computed
gaetano-signorelli/Attention-Style-Transfer/src/architecture/layers/adaptive_attention_layer.py
pointer only (licence: NONE) · get_code("0014631263abc63f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gaetano-signorelli/Attention-Style-Transfer 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.

NormalizeLayer Ran
ran on a synthesized input · constructed an object; no result was computed
gaetano-signorelli/Attention-Style-Transfer/src/architecture/layers/adaptive_attention_layer.py
pointer only (licence: NONE) · get_code("7445920a4db7720f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gaetano-signorelli/Attention-Style-Transfer 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.

calc_mean_std Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from sonnguyen129/SANet-pytorch
pointer only · get_code("38eaf8511dc7bc9c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

mean_variance_norm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from sonnguyen129/SANet-pytorch
pointer only · get_code("19f218161cc28c54")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
calc_mean_std
brick of this paper's assembly: helper
26 other papers
8 dated earlier, 17 later, 1 same year, order not determinable · 4 only as an assembly brick
1703.06868 (2017-03)
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
1812.02342 (2018-12)
Arbitrary Style Transfer with Style-Attentional Networks
1911.10033 (2019-11)
Domain Adaptation for Object Detection via Style Consistency
and 23 more not named here
mean_variance_norm
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
1812.02342 (2018-12)
Arbitrary Style Transfer with Style-Attentional Networks

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

Fast arbitrary neural style transfer has attracted widespread attention from academic, industrial and art communities due to its flexibility in enabling various applications. Existing solutions either attentively fuse deep style feature into deep content feature without considering feature distributions, or adaptively normalize deep content feature according to the style such that their global statistics are matched. Although effective, leaving shallow feature unexplored and without locally considering feature statistics, they are prone to unnatural output with unpleasing local distortions. To alleviate this problem, in this paper, we propose a novel attention and normalization module, named Adaptive Attention Normalization (AdaAttN), to adaptively perform attentive normalization on per-point basis. Specifically, spatial attention score is learnt from both shallow and deep features of content and style images. Then perpoint weighted statistics are calculated by regarding a style feature point as a distribution of attention-weighted output of all style feature points. Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics. Besides, a novel local feature loss is derived based on AdaAttN to enhance local visual quality. We also extend AdaAttN to be ready for video style transfer with slight modifications. Experiments demonstrate that our method achieves state-of-the-art arbitrary image/video style transfer. Codes and models are available on https://github.com/wzmsltw/AdaAttN.

For agents

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

get_harvested_code_for_paper("2108.03647")
get_code_for_paper("2108.03647")
have("2108.03647")

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

curl https://syntology.ai/api/ran/2108.03647.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.03647.svg)](https://syntology.ai/paper/2108.03647)

Connect an agent — have() is free.