无需梯度或模型信息，实现隐私保护的联邦语义分割
Federated Black-Box Adaptation for Semantic Segmentation
- 用零阶优化替代梯度传输，客户端仅需输出预测结果
- 在Cityscapes、CamVid等数据集上达到90%以上基准精度
- 适合医疗影像等敏感数据场景下的安全协作建模
联邦学习（FL）允许多个机构在不共享原始数据的前提下协同训练全局模型，保护数据隐私。然而，现有方法仍可能通过传递的梯度或已知的客户端模型结构还原训练数据。本文提出BlackFed框架，首次实现无需知晓模型架构且不传输梯度的联邦语义分割。该方法采用零阶优化（ZOO）更新客户端权重，一阶优化（FOO）更新服务器权重，仅依赖客户端输出的预测结果进行通信。我们在多个计算机视觉与医学影像数据集（如Cityscapes、CamVid、ACDC）上验证了其有效性，结果显示在保持高精度的同时显著增强隐私保护能力。据我们所知，这是首个完全脱离梯度与模型信息交换的联邦分割工作。
原文摘要 · Abstract (English)
Federated Learning (FL) is a form of distributed learning that allows multiple institutions or clients to collaboratively learn a global model to solve a task. This allows the model to utilize the information from every institute while preserving data privacy. However, recent studies show that the promise of protecting the privacy of data is not upheld by existing methods and that it is possible to recreate the training data from the different institutions. This is done by utilizing gradients transferred between the clients and the global server during training or by knowing the model architecture at the client end. In this paper, we propose a federated learning framework for semantic segmentation without knowing the model architecture nor transferring gradients between the client and the server, thus enabling better privacy preservation. We propose BlackFed - a black-box adaptation of neural networks that utilizes zero order optimization (ZOO) to update the client model weights and first order optimization (FOO) to update the server weights. We evaluate our approach on several computer vision and medical imaging datasets to demonstrate its effectiveness. To the best of our knowledge, this work is one of the first works in employing federated learning for segmentation, devoid of gradients or model information exchange. Code: https://github.com/JayParanjape/blackfed/tree/master
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。