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

2023-11-03 · Chicago Y. Park, Weijie Gan, Zihao Zou, Yuyang Hu, Zhixin Sun, Ulugbek S. Kamilov

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 .

📄 PDF Abstract BibTeX arXiv:2311.02003

Code (1)

wustl-cig/mbdl_pruning 공식 구현 pytorch

Tasks

Deep LearningImage Reconstruction Image Super-Resolution Network Pruning Super-Resolution

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Pruning 설명 없음

SPADE SPADE, or Spatially-Adaptive Normalization is a conditional normalization method for semantic image synthesis. Similar to [Batch…

ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks

2025-05-12 · Wenhao Hu, Paul Henderson, José Cano

Pruning is a widely used method for compressing Deep Neural Networks (DNNs), where less relevant parameters are removed from a DNN model to reduce its size. However, removing parameters reduces model accuracy, so pruning…

Prior Gradient Mask Guided Pruning-Aware Fine-Tuning

2022-02-15 · AAAI 2022 2 · Linhang Cai, Zhulin An, Chuanguang Yang, Yangchun Yan 외

We proposed a Prior Gradient Mask Guided Pruning-aware Fine-Tuning (PGMPF) framework to accelerate deep Convolutional Neural Networks (CNNs). In detail, the proposed PGMPF selectively suppresses the gradient of those ”un…

image-classification Image Classification

TT-MPD: Test Time Model Pruning and Distillation

2024-12-10 · Haihang Wu, Wei Wang, Tamasha Malepathirana, Sachith Seneviratne 외

Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dataset for both pruning and subsequent fin…

Knowledge Distillation model Pseudo Label

All-in-One Tuning and Structural Pruning for Domain-Specific LLMs

2024-12-19 · Lei Lu, Zhepeng Wang, Runxue Bao, Mengbing Wang 외

Existing pruning techniques for large language models (LLMs) targeting domain-specific applications typically follow a two-stage process: pruning the pretrained general-purpose LLMs and then fine-tuning the pruned LLMs o…

All

ICP: Immediate Compensation Pruning for Mid-to-high Sparsity

2025-01-01 · CVPR 2025 1 · Xin Luo, Xueming Fu, Zihang Jiang, S. Kevin Zhou

The increasing adoption of large-scale models under 7 billion parameters in both language and vision domains enables inference tasks on a single consumer-grade GPU but makes fine-tuning models of this scale, especial…

GPU