EESiamese: Energy-efficient Siamese Neural Network for Constrained Devices

As the deployment of artificial intelligence applications continues to expand, the demand for energy-efficient models tailored for resource-constrained devices has become increasingly critical. This paper introduces a novel approach to address this challenge by proposing an Energy-Efficient Siamese Neural Network (EESiamese) specifically designed for constrained devices such as edge computing platforms, IoT devices, and other low-power computing environments deployment. The EESiamese architecture is carefully crafted to optimize both accuracy and energy consumption. Through systematically exploring model architectures and hyperparameters, we present a fine-tuned EESiamese model that achieves competitive performance compared to traditional Siamese networks while significantly mitigating the energy overhead. Extensive experiments are conducted across a variety of constrained devices to validate the efficacy of the proposed EESiamese model in real-world scenarios. The findings demonstrate the high energy efficiency of the EESiamese, which is executed in a fraction of a millisecond and maintains an accuracy greater than 96%.