SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.12502 · ICCV · 2023

Cross Contrasting Feature Perturbation for Domain Generalization

Jianguo Zhang, Daoan Zhang, Wenjian Huang, Chenming Li

arXiv · PDF · Open in the Atlas

Code that ran

17 of 25 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 8 failures of our instrument; 8 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/2307.12502.json · badge: /api/ran/2307.12502.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
hackmebroo/ccfp canonical (classifier label)
classifier basis: census
11 ran · 3 no recorded run
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization marked official in Papers with Code
Papers with Code archive
6 ran · 5 no recorded run
FunctionStatusWhere it lives
Algorithm Ran
ran on a synthesized input · constructed an object; no result was computed
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("d4ab1855fefe42b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

DistributionUncertainty Ran
ran on a synthesized input · constructed an object; no result was computed
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("81427628d9da40b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

LDP Ran
ran on a synthesized input · constructed an object; no result was computed
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("d797b51129873a03")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

MNIST_CNN Ran
ran on a synthesized input · constructed an object; no result was computed
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("f96170b86db20ebd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

MNIST_CNN_tea Ran
ran on a synthesized input · constructed an object; no result was computed
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("f9d8f82d3edc5026")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

PermuteAdaptiveInstanceNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("04b8476374907676")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

adaptive_instance_normalization Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hackmebroo/ccfp/networks.py
pointer only (licence: NONE) · get_code("7d65990d684d50e8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/ccfp 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)
hackmebroo/ccfp/networks.py
pointer only (licence: NONE) · get_code("7dc5cc1a5cc56434")
How it ran

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

conv3x3 Ran
ran; our contract draft was wrong, not the code
hackmebroo/ccfp/resnet_mixstyle.py
pointer only (licence: NONE); 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: GitHub detected no licence in this paper's repository, hackmebroo/ccfp 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.

distance Ran
ran, honoured the contract we drafted
hackmebroo/ccfp/lib/misc.py
pointer only (licence: NONE) · get_code("fbb8c05a0a7696ec")
How it ran

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

format_mean Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hackmebroo/ccfp/collect_results.py
pointer only (licence: NONE); the stored copy get_code serves, from alexrame/fishr, is pointer only (licence: GPL-3.0) · get_code("d6d6cc53be32629d")
How it ran

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

get_test_records Ran
ran; our contract draft was wrong, not the code
hackmebroo/ccfp/model_selection.py
pointer only (licence: NONE) · get_code("53fac8d8d949e72b")
How it ran

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

hashable Ran
ran, honoured the contract we drafted
hackmebroo/ccfp/lib/query.py
pointer only (licence: NONE) · get_code("71a3a61ceed99bf3")
How it ran

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

l2_between_dicts Ran
ran, honoured the contract we drafted
hackmebroo/ccfp/lib/misc.py
pointer only (licence: NONE) · get_code("1fdaff04251a0d51")
How it ran

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

make_selector_fn Ran
ran; our contract draft was wrong, not the code
hackmebroo/ccfp/lib/query.py
pointer only (licence: NONE) · get_code("2f8af5779e1edcb6")
How it ran

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

proj Ran
ran; our contract draft was wrong, not the code
hackmebroo/ccfp/lib/misc.py
pointer only (licence: NONE) · get_code("17202e0de9779f70")
How it ran

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

remove_batch_norm_from_resnet Ran
ran; our contract draft was wrong, not the code
hackmebroo/ccfp/networks.py
pointer only (licence: NONE) · get_code("196cab71d7129d62")
How it ran

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

CCFP Not yet run
unverified (harvested, no recorded run)
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("f1069937af8d8db4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

ERM Not yet run
unverified (harvested, no recorded run)
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("50d94f70eea6617f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

Featurizer Not yet run
unverified (harvested, no recorded run)
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("9e043048978eb855")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

ResNet Not yet run
unverified (harvested, no recorded run)
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("05738dcd81fa595f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

ResNet_tea Not yet run
unverified (harvested, no recorded run)
hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/algorithms.py
pointer only (licence: NONE) · get_code("675b4e8d991b4e8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization 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.

get_algorithm_class Not yet run
unverified (harvested, no recorded run)
hackmebroo/ccfp/algorithms.py
pointer only (licence: NONE) · get_code("b0bc80b1655a6802")
How it ran

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

get_dataset_class Not yet run
unverified (harvested, no recorded run)
hackmebroo/ccfp/datasets.py
pointer only (licence: NONE) · get_code("d0ea85d74c20dea9")
How it ran

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

num_environments Not yet run
unverified (harvested, no recorded run)
hackmebroo/ccfp/datasets.py
pointer only (licence: NONE) · get_code("73f32252eedba6a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hackmebroo/ccfp 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 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 15 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 8 the same month, 11 later) and 10 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
489 dated earlier, 8 the same month, 182 later, 7 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
get_algorithm_class 39 other papers
27 dated earlier, 2 the same month, 10 later
1907.02893 (2019-07)
Invariant Risk Minimization
2007.01434 (2020-07)
In Search of Lost Domain Generalization
2007.02931 (2020-07)
Adaptive Risk Minimization: Learning to Adapt to Domain Shift
and 36 more not named here
remove_batch_norm_from_resnet 23 other papers
12 dated earlier, 2 the same month, 9 later
1907.02893 (2019-07)
Invariant Risk Minimization
2106.02266 (2021-06)
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
2111.12853 (2021-11)
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains
and 20 more not named here
get_test_records 22 other papers
13 dated earlier, 1 the same month, 8 later
1710.03077 (2017-10)
Deeper, Broader and Artier Domain Generalization
1907.02893 (2019-07)
Invariant Risk Minimization
2106.02266 (2021-06)
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
and 19 more not named here
get_dataset_class 21 other papers
15 dated earlier, 2 the same month, 4 later
1907.02893 (2019-07)
Invariant Risk Minimization
2007.01434 (2020-07)
In Search of Lost Domain Generalization
2106.02266 (2021-06)
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
and 18 more not named here
num_environments 21 other papers
13 dated earlier, 1 the same month, 7 later
1907.02893 (2019-07)
Invariant Risk Minimization
2007.01434 (2020-07)
In Search of Lost Domain Generalization
2106.02266 (2021-06)
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
and 18 more not named here
hashable 20 other papers
12 dated earlier, 1 the same month, 7 later
2106.02266 (2021-06)
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
2111.12853 (2021-11)
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains
2203.10789 (2022-03)
Domain Generalization by Mutual-Information Regularization with Pre-trained Models
and 17 more not named here
make_selector_fn 20 other papers
12 dated earlier, 1 the same month, 7 later
2106.02266 (2021-06)
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
2111.12853 (2021-11)
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains
2203.10789 (2022-03)
Domain Generalization by Mutual-Information Regularization with Pre-trained Models
and 17 more not named here
l2_between_dicts 9 other papers
6 dated earlier, 3 later
1907.02893 (2019-07)
Invariant Risk Minimization
2205.09739 (2022-05)
Diverse Weight Averaging for Out-of-Distribution Generalization
2205.13462 (2022-05)
FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
and 6 more not named here
distance 4 other papers
2 dated earlier, 2 later · 1 only as an assembly brick
2106.03632 (2021-06)
Quantifying and Improving Transferability in Domain Generalization
2106.07847 (2021-06)
Learning Stable Classifiers by Transferring Unstable Features
2401.14846 (2024-01)
Understanding Domain Generalization: A Noise Robustness Perspective
and 1 more not named here
proj 4 other papers
2 dated earlier, 2 later · 1 only as an assembly brick
2106.03632 (2021-06)
Quantifying and Improving Transferability in Domain Generalization
2106.07847 (2021-06)
Learning Stable Classifiers by Transferring Unstable Features
2401.14846 (2024-01)
Understanding Domain Generalization: A Noise Robustness Perspective
and 1 more not named here
format_mean 2 other papers
2 dated earlier
2109.02934 (2021-09)
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
2210.06807 (2022-10)
Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors
DistributionUncertainty
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2202.03958 (2022-02)
Uncertainty Modeling for Out-of-Distribution Generalization
adaptive_instance_normalization
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2010.05785 (2020-10)
Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification
calc_mean_std
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2010.05785 (2020-10)
Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification

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

Domain generalization (DG) aims to learn a robust model from source domains that generalize well on unseen target domains. Recent studies focus on generating novel domain samples or features to diversify distributions complementary to source domains. Yet, these approaches can hardly deal with the restriction that the samples synthesized from various domains can cause semantic distortion. In this paper, we propose an online one-stage Cross Contrasting Feature Perturbation (CCFP) framework to simulate domain shift by generating perturbed features in the latent space while regularizing the model prediction against domain shift. Different from the previous fixed synthesizing strategy, we design modules with learnable feature perturbations and semantic consistency constraints. In contrast to prior work, our method does not use any generative-based models or domain labels. We conduct extensive experiments on a standard DomainBed benchmark with a strict evaluation protocol for a fair comparison. Comprehensive experiments show that our method outperforms the previous state-of-the-art, and quantitative analyses illustrate that our approach can alleviate the domain shift problem in out-of-distribution (OOD) scenarios.

For agents

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

get_harvested_code_for_paper("2307.12502")
get_code_for_paper("2307.12502")
have("2307.12502")

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

curl https://syntology.ai/api/ran/2307.12502.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.12502.svg)](https://syntology.ai/paper/2307.12502)

Connect an agent — have() is free.