{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-structured-pruning-algorithm-for-model","title":"Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning","arxiv_id":"2311.02003","date":"2023-11-03","proceeding":null,"authors":["Chicago Y. Park","Weijie Gan","Zihao Zou","Yuyang Hu","Zhixin Sun","Ulugbek S. Kamilov"],"abstract":"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 .","url_abs":"https://arxiv.org/abs/2311.02003v2","url_pdf":"https://arxiv.org/pdf/2311.02003v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-structured-pruning-algorithm-for-model","repo_url":"https://github.com/wustl-cig/mbdl_pruning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"network-pruning","task_name":"Network Pruning"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"spade","method_name":"SPADE"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}