Papers › Self-Challenging Improves Cross-Domain Generalization

Self-Challenging Improves Cross-Domain Generalization

5 Jul 2020ECCV 2020 8arXiv:2007.02454archive 2025-07-28

Zeyi Huang, Haohan Wang, Eric P. Xing, Dong Huang

Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. When the training and testing data are under similar distributions, their dominant features are similar, which usually facilitates decent performance on the testing data. The performance is nonetheless unmet when tested on samples from different distributions, leading to the challenges in cross-domain image classification. We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data. RSC iteratively challenges (discards) the dominant features activated on the training data, and forces the network to activate remaining features that correlates with labels. This process appears to activate feature representations applicable to out-of-domain data without prior knowledge of new domain and without learning extra network parameters. We present theoretical properties and conditions of RSC for improving cross-domain generalization. The experiments endorse the simple, effective and architecture-agnostic nature of our RSC method.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 3 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 7 samples from 3 repositories, 6 ran (4 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 6 samples that ran have no recorded date.

CiaoHe/Nex_RSC mentioned on GitHubpytorchBSD-2-ClauseSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
DarioFontanel/OWR-VisualDomains mentioned on GitHubpytorchSyntology: not harvested report
DeLightCMU/RSC mentioned on GitHubpytorchBSD-2-ClauseSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
EscVM/RSC-Wrapper mentioned on GitHubtfApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
HaohanWang/ImageNet-Sketch mentioned on GitHubpytorchMITSyntology: not harvested report
cherise215/maxstyle mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Virtual Adversarial Training: A Regularization Method for Supervised and... (arXiv:1704.03976; that paper's own run record: 11 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
dnap512/SelfReg mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SelfReg: Self-supervised Contrastive Regularization for Domain Generalization (arXiv:2104.09841; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
facebookresearch/DomainBed mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Domain-Adversarial Training of Neural Networks (arXiv:1505.07818; that paper's own run record: 35 ran (of which 11 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 17 where Syntology's instrument failed) · 17 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Deep CORAL: Correlation Alignment for Deep Domain Adaptation (arXiv:1607.01719; that paper's own run record: 10 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified) and 8 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
4ran
1unverified

Licence: 1 of the 7 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

CiaoHe/Nex_RSC community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_optim_and_scheduler in 5 papers Domain_Generalization/optimizer/optimizer_helper.py ran BSD-2-Clause (permissive) here; the stored copy is pointer only · 52231145e6cbb0b4 · report fixture: signature network:callable/0/?, epochs:int/0/int, lr:float/0/float, train_all:bool/0/bool, nesterov:bool/0/bool · returned tuple · level recorded 2026-09-24
DeLightCMU/RSC community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
conv1x1 in 691 papers ImageNet/resnet.py ran · our draft was wrong BSD-2-Clause (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers ImageNet/resnet.py ran · our draft was wrong BSD-2-Clause (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
resnet18 in 432 papers ImageNet/resnet.py unverified BSD-2-Clause (permissive) · b7acfb34cb504027 · report
EscVM/RSC-Wrapper community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
grayscale utils/data_augmentation_pacs.py ran Apache-2.0 (permissive) · c72ea600b55ead51 · report fixture: signature x:EagerTensor/4/int, y:EagerTensor/1/int · returned tuple · level recorded 2026-09-25
horizontal_flip in 12 papers utils/data_augmentation_pacs.py ran Apache-2.0 (permissive) · 49b9eb19eaab3cd4 · report fixture: signature x:EagerTensor/4/int, y:EagerTensor/1/int · returned tuple · level recorded 2026-09-24
random_crop in 59 papers utils/data_augmentation_pacs.py ran Apache-2.0 (permissive) · ca3b7595e2160b63 · report fixture: signature x:EagerTensor/3/float, y:EagerTensor/0/int · returned tuple · level recorded 2026-09-25

Tasks

Domain GeneralizationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization Office-Home RSC (ResNet18) Average Accuracy 63.12 #43 of 45 Archive leaderboard report
Domain Generalization PACS RSC (ResNet-50) Average Accuracy 87.83 #35 of 133 Archive leaderboard report
Domain Generalization PACS RSC (Resnet-50, DomainBed) Average Accuracy 85.2 #53 of 133 Archive leaderboard report
Domain Generalization PACS RSC (Resnet-18) Average Accuracy 85.15 #54 of 133 Archive leaderboard report
Domain Generalization PACS RSC (AlexNet) Average Accuracy 76.05 #102 of 133 Archive leaderboard report
Domain Generalization VLCS RSC (AlexNet) Average Accuracy 75.43 #36 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections