9 citations · 17 across the 8 of their papers we have counts for
3 papers · 1 filter
Reducing Inference Energy Consumption Using Dual Complementary CNNs
Michail Kinnas, John Violos, Ioannis Kompatsiaris +1
Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of the…
A New Approach for Evaluating the Performance of Distributed Latency-Sensitive Services
Theodoros Theodoropoulos, John Violos, Antonios Makris +1
Conventional latency metrics are formulated based on a broad definition of traditional monolithic services, and hence lack the capacity to address the complexities inherent in mode…
Towards Optimal Trade-offs in Knowledge Distillation for CNNs and Vision Transformers at the Edge
John Violos, Symeon Papadopoulos, Ioannis Kompatsiaris
This paper discusses four facets of the Knowledge Distillation (KD) process for Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures, particularly when e…