arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.02003eess.IVcs.CV
收藏

基于模型的高效深度学习:通过网络剪枝与微调实现

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

Washington University in St. Louis(圣路易斯华盛顿大学)

Chicago Y. Park, Weijie Gan, Zihao Zou, Yuyang Hu, Zhixin Sun, Ulugbek S. Kamilov

AI总结:

本文提出通过结构化剪枝减少MBDL网络参数,并提供三种微调策略以缓解性能损失,使基于DEQ和DU的图像重建分别加速50%和32%且几乎无性能损失。

摘要:

基于模型的深度学习(MBDL)是一种设计深度模型以解决成像逆问题的强大方法论。MBDL网络可被视为迭代算法,利用物理测量模型和由卷积神经网络(CNN)指定的学习图像先验来估计目标图像。MBDL网络的迭代特性增加了测试时的计算复杂度,限制了其在某些大规模应用中的适用性。在此,我们提出两项贡献以解决这一问题:首先,我们展示了如何采用结构化剪枝来减少MBDL网络中的参数数量。其次,我们提出了三种方法来微调剪枝后的MBDL网络,以缓解潜在的性能损失。每种微调策略都有其独特优势,具体取决于是否存在预训练模型和高质量真值。我们证明,我们的剪枝与微调方法可使基于流行的深度均衡学习(DEQ)和深度展开(DU)方法的图像重建分别加速50%和32%,且几乎没有性能损失。因此,这项工作通过展示剪枝在提升MBDL可扩展性方面的潜力,为解决逆问题迈出了一步。代码可在https://github.com/wustl-cig/MBDL_Pruning获取。

英文摘要:

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 .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑