Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AI
This is an incremental survey paper that reviews existing methods to improve efficiency in biometric deep learning, targeting researchers and practitioners in security and edge computing.
The paper surveys efficient deep learning methods for biometric applications, addressing challenges like high energy consumption and resource constraints, and proposes a taxonomy and evaluation metrics for model efficiency.
Recent advances in deep learning, whether on discriminative or generative tasks have been beneficial for various applications, among which security and defense. However, their increasing computational demands during training and deployment translates directly into high energy consumption. As a consequence, this induces a heavy carbon footprint which hinders their widespread use and scalability, but also a limitation when deployed on resource-constrained edge devices for real-time use. In this paper, we briefly survey efficient deep learning methods for biometric applications. Specifically, we tackle the challenges one might incur when training and deploying deep learning approaches, and provide a taxonomy of the various efficient deep learning families. Additionally, we discuss complementary metrics for evaluating the efficiency of these models such as memory, computation, latency, throughput, and advocate for universal and reproducible metrics for better comparison. Last, we give future research directions to consider.