在边缘设备上用低秩技术实现快速图像检测，节省算力与通信开销。
Federated Learning of Low-Rank One-Shot Image Detection Models in Edge Devices with Scalable Accuracy and Compute Complexity
- 用低秩适配改进单次学习检测模型，降低计算和通信负担。
- 在MNIST和CIFAR10上达到良好检测性能，通信量与算力显著下降。
- 适合资源受限的异构边缘设备，支持高效协同训练。
本文提出一种新型联邦学习框架LoRa-FL，用于在边缘设备上训练低秩单次图像检测模型。通过将低秩适配技术融入单次检测架构，该方法显著降低计算与通信开销，同时保持可扩展的准确率。框架利用联邦学习协同训练轻量化图像识别模型，实现在异构、资源受限设备上的快速适应与高效部署。在MNIST和CIFAR10基准数据集上的实验表明，无论在独立同分布（IID）还是非独立同分布（non-IID）设置下，该方法均实现了具有竞争力的检测性能，同时大幅减少通信带宽和计算复杂度。这使其成为降低通信与算力开销的有前景方案，且不牺牲模型准确率。
原文摘要 · Abstract (English)
This paper introduces a novel federated learning framework termed LoRa-FL designed for training low-rank one-shot image detection models deployed on edge devices. By incorporating low-rank adaptation techniques into one-shot detection architectures, our method significantly reduces both computational and communication overhead while maintaining scalable accuracy. The proposed framework leverages federated learning to collaboratively train lightweight image recognition models, enabling rapid adaptation and efficient deployment across heterogeneous, resource-constrained devices. Experimental evaluations on the MNIST and CIFAR10 benchmark datasets, both in an independent-and-identically-distributed (IID) and non-IID setting, demonstrate that our approach achieves competitive detection performance while significantly reducing communication bandwidth and compute complexity. This makes it a promising solution for adaptively reducing the communication and compute power overheads, while not sacrificing model accuracy.
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。