{"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/ordinal-pooling-networks-for-preserving","title":"Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps","arxiv_id":"1804.02702","date":"2018-04-08","proceeding":null,"authors":["Ashwani Kumar"],"abstract":"In the framework of convolutional neural networks that lie at the heart of\ndeep learning, downsampling is often performed with a max-pooling operation\nthat only retains the element with maximum activation, while completely\ndiscarding the information contained in other elements in a pooling region. To\naddress this issue, a novel pooling scheme, Ordinal Pooling Network (OPN), is\nintroduced in this work. OPN rearranges all the elements of a pooling region in\na sequence and assigns different weights to these elements based upon their\norders in the sequence, where the weights are learned via the gradient-based\noptimisation. The results of our small-scale experiments on image\nclassification task demonstrate that this scheme leads to a consistent\nimprovement in the accuracy over max-pooling operation. This improvement is\nexpected to increase in deeper networks, where several layers of pooling become\nnecessary.","url_abs":"http://arxiv.org/abs/1804.02702v2","url_pdf":"http://arxiv.org/pdf/1804.02702v2.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":"ordinal-pooling-networks-for-preserving","repo_url":"https://github.com/ash80/Ordinal-Pooling-Networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.02702","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}