aalto1 untyped-item.component.html

Improving robustness to corruptions with multiplicative weight perturbations

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Advances in Neural Information Processing Systems ; Volume 37

Abstract

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.

Description

| openaire: EC/H2020/951847/EU//ELISE

Keywords

Other note

Citation

Trinh, T, Heinonen, M, Acerbi, L & Kaski, S 2025, Improving robustness to corruptions with multiplicative weight perturbations. in A Globerson, L Mackey, D Belgrave, A Fan, U Paquet, J Tomczak & C Zhang (eds), Advances in Neural Information Processing Systems 37 (NeurIPS 2024). Advances in Neural Information Processing Systems, vol. 37, Curran Associates Inc., Conference on Neural Information Processing Systems, Vancouver, Canada, 10/12/2024. https://doi.org/001633298300271

Endorsement

Review

Supplemented By

Referenced By