Privacy-Preserving ConvMixer Without Any Accuracy Degradation Using Compressible Encrypted Images
We propose an enhanced privacy-preserving method for image classification using ConvMixer, which is an extremely simple model that is similar in spirit to the Vision Transformer (ViT). Most privacy-preserving methods using encrypted images cause the performance of models to degrade due to the influe...
Sparad:
| Huvudupphov: | , , |
|---|---|
| Materialtyp: | Artigo |
| Språk: | Inglês |
| Utgiven: |
MDPI AG
2024-11-01
|
| Serie: | Information |
| Ämnen: | |
| Länkar: | https://www.mdpi.com/2078-2489/15/11/723 |
| Taggar: |
Inga taggar, Lägg till första taggen!
|