Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Park, Chicago Y., Gan, Weijie, Zou, Zihao, Hu, Yuyang, Sun, Zhixin, Kamilov, Ulugbek S.
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916672203390976
author Park, Chicago Y.
Gan, Weijie
Zou, Zihao
Hu, Yuyang
Sun, Zhixin
Kamilov, Ulugbek S.
author_facet Park, Chicago Y.
Gan, Weijie
Zou, Zihao
Hu, Yuyang
Sun, Zhixin
Kamilov, Ulugbek S.
contents Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and a learned image prior specified using a convolutional neural net (CNNs). The iterative nature of MBDL networks increases the test-time computational complexity, which limits their applicability in certain large-scale applications. Here we make two contributions to address this issue: First, we show how structured pruning can be adopted to reduce the number of parameters in MBDL networks. Second, we present three methods to fine-tune the pruned MBDL networks to mitigate potential performance loss. Each fine-tuning strategy has a unique benefit that depends on the presence of a pre-trained model and a high-quality ground truth. We show that our pruning and fine-tuning approach can accelerate image reconstruction using popular deep equilibrium learning (DEQ) and deep unfolding (DU) methods by 50% and 32%, respectively, with nearly no performance loss. This work thus offers a step forward for solving inverse problems by showing the potential of pruning to improve the scalability of MBDL. Code is available at https://github.com/wustl-cig/MBDL_Pruning .
format Preprint
id arxiv_https___arxiv_org_abs_2311_02003
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning
Park, Chicago Y.
Gan, Weijie
Zou, Zihao
Hu, Yuyang
Sun, Zhixin
Kamilov, Ulugbek S.
Image and Video Processing
Computer Vision and Pattern Recognition
Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and a learned image prior specified using a convolutional neural net (CNNs). The iterative nature of MBDL networks increases the test-time computational complexity, which limits their applicability in certain large-scale applications. Here we make two contributions to address this issue: First, we show how structured pruning can be adopted to reduce the number of parameters in MBDL networks. Second, we present three methods to fine-tune the pruned MBDL networks to mitigate potential performance loss. Each fine-tuning strategy has a unique benefit that depends on the presence of a pre-trained model and a high-quality ground truth. We show that our pruning and fine-tuning approach can accelerate image reconstruction using popular deep equilibrium learning (DEQ) and deep unfolding (DU) methods by 50% and 32%, respectively, with nearly no performance loss. This work thus offers a step forward for solving inverse problems by showing the potential of pruning to improve the scalability of MBDL. Code is available at https://github.com/wustl-cig/MBDL_Pruning .
title Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.02003