A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique

Homare Sueyoshi, Kiyoshi Nishikawa, Hitoshi Kiya

2025-07-17Segmentation Semantic Segmentation Privacy Preserving Domain Adaptation

Abstract

We propose a privacy-preserving semantic-segmentation method for applying perceptual encryption to images used for model training in addition to test images. This method also provides almost the same accuracy as models without any encryption. The above performance is achieved using a domain-adaptation technique on the embedding structure of the Vision Transformer (ViT). The effectiveness of the proposed method was experimentally confirmed in terms of the accuracy of semantic segmentation when using a powerful semantic-segmentation model with ViT called Segmentation Transformer.

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21 Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17 DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17 From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17 Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17 SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17 Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17 Federated Learning for Commercial Image Sources2025-07-17