{"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/the-multi-lane-capsule-network-mlcn","title":"The Multi-Lane Capsule Network (MLCN)","arxiv_id":"1902.08431","date":"2019-02-22","proceeding":null,"authors":["Vanderson Martins do Rosario","Edson Borin","Mauricio Breternitz Jr"],"abstract":"We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and\nresource efficient organization of Capsule Networks (CapsNet) that allows\nparallel processing, while achieving high accuracy at reduced cost. A MLCN is\ncomposed of a number of (distinct) parallel lanes, each contributing to a\ndimension of the result, trained using the routing-by-agreement organization of\nCapsNet. Our results indicate similar accuracy with a much reduced cost in\nnumber of parameters for the Fashion-MNIST and Cifar10 datsets. They also\nindicate that the MLCN outperforms the original CapsNet when using a proposed\nnovel configuration for the lanes. MLCN also has faster training and inference\ntimes, being more than two-fold faster than the original CapsNet in the same\naccelerator.","url_abs":"http://arxiv.org/abs/1902.08431v1","url_pdf":"http://arxiv.org/pdf/1902.08431v1.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":"the-multi-lane-capsule-network-mlcn","repo_url":"https://github.com/vandersonmr/lanes-capsnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"the-multi-lane-capsule-network-mlcn","repo_url":"https://github.com/lmcad-unicamp/lanes-capsnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}