Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy
This addresses sustainability concerns in AI by providing empirical data and tools for energy-efficient model selection, though it's incremental in analyzing existing models rather than proposing new methods.
The study analyzed inference energy consumption of 1,200 ImageNet classification models, revealing steep diminishing returns in accuracy gains relative to energy usage increases, and introduced an energy efficiency scoring system with an interactive web application.
Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of comprehensive understanding of their energy efficiency during inference. In this study, we conduct a comprehensive analysis of the inference energy consumption of 1,200 ImageNet classification models - the largest evaluation of its kind to date. Our findings reveal a steep diminishing return in accuracy gains relative to the increase in energy usage, highlighting sustainability concerns in the pursuit of marginal improvements. We identify key factors contributing to energy consumption and demonstrate methods to improve energy efficiency. To promote more sustainable AI practices, we introduce an energy efficiency scoring system and develop an interactive web application that allows users to compare models based on accuracy and energy consumption. By providing extensive empirical data and practical tools, we aim to facilitate informed decision-making and encourage collaborative efforts in developing energy-efficient AI technologies.