Papers › Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks...

Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain

19 Aug 2021ICCV 2021 10arXiv:2108.08487archive 2025-07-28

Guangyao Chen, Peixi Peng, Li Ma, Jia Li, Lin Du, Yonghong Tian

Recently, the generalization behavior of Convolutional Neural Networks (CNN) is gradually transparent through explanation techniques with the frequency components decomposition. However, the importance of the phase spectrum of the image for a robust vision system is still ignored. In this paper, we notice that the CNN tends to converge at the local optimum which is closely related to the high-frequency components of the training images, while the amplitude spectrum is easily disturbed such as noises or common corruptions. In contrast, more empirical studies found that humans rely on more phase components to achieve robust recognition. This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image. That is, the generated samples force the CNN to pay more attention to the structured information from phase components and keep robust to the variation of the amplitude. Experiments on several image datasets indicate that the proposed method achieves state-of-the-art performances on multiple generalizations and calibration tasks, including adaptability for common corruptions and surface variations, out-of-distribution detection, and adversarial attack.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.08487")

Code

Syntology Ran 9 of 10 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · honoured contract; 7 ran · our draft was wrong.

By repository: official repository: 10 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

iCGY96/APR officialmentioned in papermentioned on GitHubpytorch 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.

Code Syntology ran Syntology

10 samples harvested; 9 ran; 2 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
7ran · our draft was wrong
1unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from iCGY96/APR. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

float_parameter iCGY96/APR/datasets/APR.py official repository ran · honoured contract MIT (permissive) · be1cf2403304fa6d · report
int_parameter iCGY96/APR/datasets/APR.py official repository ran · honoured contract fingerprinted MIT (permissive) · beaa91443124b324 · report
posterize iCGY96/APR/datasets/APR.py official repository ran · our draft was wrong MIT (permissive) · 43b678f915759923 · report
rotate iCGY96/APR/datasets/APR.py official repository ran · our draft was wrong MIT (permissive) · d85800f55f323864 · report
shear_x iCGY96/APR/datasets/APR.py official repository ran · our draft was wrong MIT (permissive) · 417bb83cee1eb445 · report
shear_y iCGY96/APR/datasets/APR.py official repository ran · our draft was wrong MIT (permissive) · 5615796e020bb66b · report
solarize iCGY96/APR/datasets/APR.py official repository ran · our draft was wrong MIT (permissive) · 62f59af34932ce5f · report
translate_x iCGY96/APR/datasets/APR.py official repository ran · our draft was wrong MIT (permissive) · 63c558f9d95b07bd · report
translate_y iCGY96/APR/datasets/APR.py official repository ran · our draft was wrong MIT (permissive) · 9497b9c7bcc19bdf · report
APRecombination iCGY96/APR/datasets/APR.py official repository unverified MIT (permissive) · 718adcc72de6cc2b · report

Tasks

Adversarial AttackData AugmentationDomain GeneralizationOut-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-C APR-SP + DeepAugment (ResNet-50) mean Corruption Error (mCE) 57.5 #35 of 47 Archive leaderboard report
Domain Generalization ImageNet-C APR-SP (ResNet-50) mean Corruption Error (mCE) 65.0 #37 of 47 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 ResNet18 + APR-P AUROC 98.1 #7 of 10 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