CycleBNN: Cyclic Precision Training in Binary Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fontana, Federico, Lanzino, Romeo, Diko, Anxhelo, Foresti, Gian Luca, Cinque, Luigi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912052660928512
author Fontana, Federico
Lanzino, Romeo
Diko, Anxhelo
Foresti, Gian Luca
Cinque, Luigi
author_facet Fontana, Federico
Lanzino, Romeo
Diko, Anxhelo
Foresti, Gian Luca
Cinque, Luigi
contents This paper works on Binary Neural Networks (BNNs), a promising avenue for efficient deep learning, offering significant reductions in computational overhead and memory footprint to full precision networks. However, the challenge of energy-intensive training and the drop in performance have been persistent issues. Tackling the challenge, prior works focus primarily on task-related inference optimization. Unlike prior works, this study offers an innovative methodology integrating BNNs with cyclic precision training, introducing the CycleBNN. This approach is designed to enhance training efficiency while minimizing the loss in performance. By dynamically adjusting precision in cycles, we achieve a convenient trade-off between training efficiency and model performance. This emphasizes the potential of our method in energy-constrained training scenarios, where data is collected onboard and paves the way for sustainable and efficient deep learning architectures. To gather insights on CycleBNN's efficiency, we conduct experiments on ImageNet, CIFAR-10, and PASCAL-VOC, obtaining competitive performances while using 96.09\% less operations during training on ImageNet, 88.88\% on CIFAR-10 and 96.09\% on PASCAL-VOC. Finally, CycleBNN offers a path towards faster, more accessible training of efficient networks, accelerating the development of practical applications. The PyTorch code is available at \url{https://github.com/fedeloper/CycleBNN/}
format Preprint
id arxiv_https___arxiv_org_abs_2410_00050
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CycleBNN: Cyclic Precision Training in Binary Neural Networks
Fontana, Federico
Lanzino, Romeo
Diko, Anxhelo
Foresti, Gian Luca
Cinque, Luigi
Machine Learning
Computer Vision and Pattern Recognition
This paper works on Binary Neural Networks (BNNs), a promising avenue for efficient deep learning, offering significant reductions in computational overhead and memory footprint to full precision networks. However, the challenge of energy-intensive training and the drop in performance have been persistent issues. Tackling the challenge, prior works focus primarily on task-related inference optimization. Unlike prior works, this study offers an innovative methodology integrating BNNs with cyclic precision training, introducing the CycleBNN. This approach is designed to enhance training efficiency while minimizing the loss in performance. By dynamically adjusting precision in cycles, we achieve a convenient trade-off between training efficiency and model performance. This emphasizes the potential of our method in energy-constrained training scenarios, where data is collected onboard and paves the way for sustainable and efficient deep learning architectures. To gather insights on CycleBNN's efficiency, we conduct experiments on ImageNet, CIFAR-10, and PASCAL-VOC, obtaining competitive performances while using 96.09\% less operations during training on ImageNet, 88.88\% on CIFAR-10 and 96.09\% on PASCAL-VOC. Finally, CycleBNN offers a path towards faster, more accessible training of efficient networks, accelerating the development of practical applications. The PyTorch code is available at \url{https://github.com/fedeloper/CycleBNN/}
title CycleBNN: Cyclic Precision Training in Binary Neural Networks
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.00050