Answers are grounded in this paper and cite their sources.
With the rapid development of deep learning, target detection algorithms have been widely used, but the traditional target detection methods need to collect a large number of labeled sensitive data, which is likely to violate user privacy and data confidentiality. As a privacy-preserving distributed machine learning method, federated learning enables end-to-end computer vision tasks, where image annotation and training tasks are moved to the edge, while only model parameters are sent to the aggregation server for aggregation. This paper proposes a kind of edge auxiliary iot intelligent recognition based on federal learning system, the system adopts the terminal layer, edge service layer, network layer and cloud center service layer four layer architecture, can analyze the distribution of detailed statistics, in the way of privacy protection, auxiliary iot devices for safe and intelligent object recognition.
No takes yet. Share an insight, caveat, or question.
A 2025 study studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: