Federated Learning for Computer Vision

TL;DR

This paper reviews recent advancements in federated learning for computer vision, highlighting its benefits, challenges, privacy concerns, and future research directions to improve decentralized ML models.

Contribution

It provides the first comprehensive review of federated learning in computer vision, including a taxonomy, security analysis, and discussion of blockchain integration.

Findings

FL reduces privacy risks compared to centralized training

FL enables distributed computation for large-scale CV tasks

Open challenges include security threats and privacy preservation methods

Abstract

Computer Vision (CV) is playing a significant role in transforming society by utilizing machine learning (ML) tools for a wide range of tasks. However, the need for large-scale datasets to train ML models creates challenges for centralized ML algorithms. The massive computation loads required for processing and the potential privacy risks associated with storing and processing data on central cloud servers put these algorithms under severe strain. To address these issues, federated learning (FL) has emerged as a promising solution, allowing privacy preservation by training models locally and exchanging them to improve overall performance. Additionally, the computational load is distributed across multiple clients, reducing the burden on central servers. This paper presents, to the best of the authors' knowledge, the first review discussing recent advancements of FL in CV applications, comparing them to conventional centralized training paradigms. It provides an overview of current FL applications in various CV tasks, emphasizing the advantages of FL and the challenges of implementing it in CV. To facilitate this, the paper proposes a taxonomy of FL techniques in CV, outlining their applications and security threats. It also discusses privacy concerns related to implementing blockchain in FL schemes for CV tasks and summarizes existing privacy preservation methods. Moving on, the paper identifies open research challenges and potential future research directions to further exploit the potential of FL and blockchain in CV applications.