Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nagamori, Teru, Shiota, Sayaka, Kiya, Hitoshi
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914671790915584
author Nagamori, Teru
Shiota, Sayaka
Kiya, Hitoshi
author_facet Nagamori, Teru
Shiota, Sayaka
Kiya, Hitoshi
contents We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT). The method allows us not only to train models and test with visually protected images but to also avoid the performance degradation caused from the use of encrypted images, whereas conventional methods cannot avoid the influence of image encryption. A domain adaptation method is used to efficiently fine-tune ViT with encrypted images. In experiments, the method is demonstrated to outperform conventional methods in an image classification task on the CIFAR-10 and ImageNet datasets in terms of classification accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05126
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer
Nagamori, Teru
Shiota, Sayaka
Kiya, Hitoshi
Computer Vision and Pattern Recognition
Machine Learning
We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT). The method allows us not only to train models and test with visually protected images but to also avoid the performance degradation caused from the use of encrypted images, whereas conventional methods cannot avoid the influence of image encryption. A domain adaptation method is used to efficiently fine-tune ViT with encrypted images. In experiments, the method is demonstrated to outperform conventional methods in an image classification task on the CIFAR-10 and ImageNet datasets in terms of classification accuracy.
title Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.05126