Papers › Improving robustness to corruptions with multiplicative weight perturbations

Improving robustness to corruptions with multiplicative weight perturbations

24 Jun 2024arXiv:2406.16540archive 2025-07-28

Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski

Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to those corruptions but may harm performance on clean images and other types of distortion. In this paper, we introduce an alternative approach that improves the robustness of DNNs to a wide range of corruptions without compromising accuracy on clean images. We first demonstrate that input perturbations can be mimicked by multiplicative perturbations in the weight space. Leveraging this, we propose Data Augmentation via Multiplicative Perturbation (DAMP), a training method that optimizes DNNs under random multiplicative weight perturbations. We also examine the recently proposed Adaptive Sharpness-Aware Minimization (ASAM) and show that it optimizes DNNs under adversarial multiplicative weight perturbations. Experiments on image classification datasets (CIFAR-10/100, TinyImageNet and ImageNet) and neural network architectures (ResNet50, ViT-S/16, ViT-B/16) show that DAMP enhances model generalization performance in the presence of corruptions across different settings. Notably, DAMP is able to train a ViT-S/16 on ImageNet from scratch, reaching the top-1 error of 23.7% which is comparable to ResNet50 without extensive data augmentations.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2406.16540")

Code

Syntology Ran 7 of 9 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 9 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

trungtrinh44/damp officialmentioned in paperjax 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

9 samples harvested; 7 ran; 3 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
2unverified

Licence: 9 of the 9 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 trungtrinh44/damp. “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.

_get_gaussian_kernel trungtrinh44/damp/randaugment/augment.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · ed852e74db36309a · report
_get_gaussian_kernel_2d trungtrinh44/damp/randaugment/augment.py official repository ran · violated contract no licence file found · pointer only · 03fcb094182e80ea · report
_normalize_tuple trungtrinh44/damp/randaugment/augment.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · a5c06a4fe76d4fc3 · report
_pad trungtrinh44/damp/randaugment/augment.py official repository ran · our draft was wrong no licence file found · pointer only · f55c98808a12d76e · report
gaussian_filter2d trungtrinh44/damp/randaugment/augment.py official repository ran · fixture could not drive it no licence file found · pointer only · c15f0fd201ea7a3a · report
open_json trungtrinh44/damp/imagenet/eval_vit_imagenet_and_imagenet_c.py official repository ran · our draft was wrong no licence file found · pointer only · a1c31b015211f700 · report
to_4d trungtrinh44/damp/randaugment/augment.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · bd1c72a9d8556505 · report
from_4d trungtrinh44/damp/randaugment/augment.py official repository unverified no licence file found · pointer only · b10fb8ac53c53a97 · report
gaussian_noise trungtrinh44/damp/randaugment/augment.py official repository unverified no licence file found · pointer only · 8cbf8b03fdf303a9 · report

Tasks

Data AugmentationImage Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Sharpness-Aware Minimization

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