用感知加密保护ViT模型检测图像隐私，精度几乎无损。
Privacy-Preserving Object Detection for Vision Transformer-Based Models
- 基于ViT嵌入结构与密钥域适应实现感知加密
- 在ViTdet上保持接近无保护时的检测精度
- 首次为视觉Transformer目标检测提供隐私保护方案
我们提出一种新型目标检测方法，可保护测试图像中的敏感视觉信息。以往关注视觉信息保护的研究集中于图像分类任务。本文首次将感知加密应用于基于视觉变换器（ViT）的目标检测。该方法利用ViT的嵌入结构与基于密钥的域适应技术，使模型在保护隐私的同时，达到与未受保护模型几乎相同的检测精度。实验在ViTdet（一种基于ViT的目标检测模型）上验证了所提方法在准确率和视觉保护方面的有效性。
原文摘要 · Abstract (English)
We propose a novel object detection method that enables us to protect sensitive visual information of test images. Previous studies considering visual information protection focus on image classification tasks. This paper proposes an object detection method using perceptual encryption for the first time. The proposed method can achieve almost the same accuracy as that of models without any protection by utilizing the embedding structure of the Vision Transformer (ViT) and a domain adaptation technique with keys. In experiments, the effectiveness of the proposed method is verified in terms of accuracy and visual protection under the use of ViTdet, which is a ViT-based object detection model.
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。