Privacy-Preserving Semantic Segmentation Using Vision Transformer

In this paper, we propose a privacy-preserving semantic segmentation method that uses encrypted images and models with the vision transformer (ViT), called the segmentation transformer (SETR). The combined use of encrypted images and SETR allows us not only to apply images without sensitive visual i...

Full description

Bibliographic Details

Main Authors:	Hitoshi Kiya, Teru Nagamori, Shoko Imaizumi, Sayaka Shiota
Format:	Artigo
Language:	Inglês
Published:	MDPI AG 2022-08-01
Series:	Journal of Imaging
Subjects:	semantic segmentation vision transformer segmentation transformer privacy-preserving
Online Access:	https://www.mdpi.com/2313-433X/8/9/233
Tags:	Add Tag No Tags, Be the first to tag this record!