用域适应技术保护视觉变换器的图像分割隐私，精度几乎不变。
A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique
- 在ViT嵌入结构上应用域适应，实现训练与测试图像的感知加密。
- 使用Segmenation Transformer模型时，分割精度接近未加密情况。
- 适合需要隐私保护的医疗、自动驾驶等视觉分割场景。
我们提出一种隐私保护的语义分割方法，对用于模型训练和测试的图像应用感知加密。该方法通过在视觉变换器（ViT）的嵌入结构上使用域适应技术，实现了与无加密情况相近的分割精度。实验验证了所提方法在使用高性能语义分割模型Segmentation Transformer时的有效性，确保了在保护隐私的同时维持高精度分割性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。