{"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/computation-performance-optimization-of","title":"Computation-Performance Optimization of Convolutional Neural Networks with Redundant Kernel Removal","arxiv_id":"1705.10748","date":"2017-05-30","proceeding":null,"authors":["Chih-Ting Liu","Yi-Heng Wu","Yu-Sheng Lin","Shao-Yi Chien"],"abstract":"Deep Convolutional Neural Networks (CNNs) are widely employed in modern\ncomputer vision algorithms, where the input image is convolved iteratively by\nmany kernels to extract the knowledge behind it. However, with the depth of\nconvolutional layers getting deeper and deeper in recent years, the enormous\ncomputational complexity makes it difficult to be deployed on embedded systems\nwith limited hardware resources. In this paper, we propose two\ncomputation-performance optimization methods to reduce the redundant\nconvolution kernels of a CNN with performance and architecture constraints, and\napply it to a network for super resolution (SR). Using PSNR drop compared to\nthe original network as the performance criterion, our method can get the\noptimal PSNR under a certain computation budget constraint. On the other hand,\nour method is also capable of minimizing the computation required under a given\nPSNR drop.","url_abs":"http://arxiv.org/abs/1705.10748v3","url_pdf":"http://arxiv.org/pdf/1705.10748v3.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":"computation-performance-optimization-of","repo_url":"https://github.com/Gideon0805/Tensorflow1.15-Model-Pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"computation-performance-optimization-of","repo_url":"https://github.com/Gideon0805/Tensorflow_Model_Pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}