Proto-SVDD: Decentralized Federated Object Detection with Prototype-Based Communication

Federated Learning (FL) methods typically require Deep Neural Network (DNN) weight transfer from FL clients to an FL aggregator (master) for centralized DNN aggregation. However, this may not be possible under strict privacy or network constraints. In this paper, we present Proto-SVDD, a fully decentralized federated learning framework for enabling collaborative DNN model training, without neural parameter sharing. Instead, Proto-SVDD employs a lightweight class-wise prototype learning mechanism based on Support Vector Data Description (SVDD), which is trained by each FL client DNN using their own local, private data. Collaboration between FL clients involves exchanging and aggregating only their SVDD class prototypes in a fully decentralized topology. Neither DNN weights nor training data are exchanged between FL nodes whatsoever. Proto-SVDD has been evaluated for the object detection task, under various DNN client configurations, demonstrating competitive object detection accuracy with a significantly lower communication cost compared with stateof-the-art prototype-based FL methods. Experimental results show that Proto-SVDD federated learning enables efficient object detection in limited resources and privacy constraint settings.