Privacy-preserving semantic segmentation using vision transformer

HIGHLIGHTS

• who: Hitoshi Kiya and collaborators from the Department of Computer Science, Tokyo Metropolitan University, Asahigaoka, Hino-shi, Tokyo, Japan have published the research: Privacy-Preserving Semantic Segmentation Using Vision Transformer, in the Journal: (JOURNAL)
• what: The authors propose a privacy-preserving semantic segmentation method that uses encrypted images and models with the (ViT) called the segmentation (SETR). The reason that the authors focus on ViT-based models is given below. The authors aim to overcome these issues in this paper. As the authors focus on protecting personally identifiable information included in an image such as . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.