EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation
Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V., Dortmund, Germany
arXiv:2306.06152 [cs.LG], (9 Jun 2023)
@misc{zhou2023efficientbioai,
title={EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation},
author={Yu Zhou and Justin Sonneck and Sweta Banerjee and Stefanie Dörr and Anika Grüneboom and Kristina Lorenz and Jianxu Chen},
year={2023},
eprint={2306.06152},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
Artificial intelligence (AI) has been widely used in bioimage image analysis nowadays, but the efficiency of AI models, like the energy consumption and latency is not ignorable due to the growing model size and complexity, as well as the fast-growing analysis needs in modern biomedical studies. Like we can compress large images for efficient storage and sharing, we can also compress the AI models for efficient applications and deployment. In this work, we present EfficientBioAI, a plug-and-play toolbox that can compress given bioimaging AI models for them to run with significantly reduced energy cost and inference time on both CPU and GPU, without compromise on accuracy. In some cases, the prediction accuracy could even increase after compression, since the compression procedure could remove redundant information in the model representation and therefore reduce over-fitting. From four different bioimage analysis applications, we observed around 2-5 times speed-up during inference and 30-80% saving in energy. Cutting the runtime of large scale bioimage analysis from days to hours or getting a two-minutes bioimaging AI model inference done in near real-time will open new doors for method development and biomedical discoveries. We hope our toolbox will facilitate resource-constrained bioimaging AI and accelerate large-scale AI-based quantitative biological studies in an eco-friendly way, as well as stimulate further research on the efficiency of bioimaging AI.
June 18, 2023 by hgpu
