{"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/an-aggregated-multicolumn-dilated-convolution","title":"An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting","arxiv_id":"1804.07821","date":"2018-04-20","proceeding":null,"authors":["Diptodip Deb","Jonathan Ventura"],"abstract":"We propose the use of dilated filters to construct an aggregation module in a\nmulticolumn convolutional neural network for perspective-free counting.\nCounting is a common problem in computer vision (e.g. traffic on the street or\npedestrians in a crowd). Modern approaches to the counting problem involve the\nproduction of a density map via regression whose integral is equal to the\nnumber of objects in the image. However, objects in the image can occur at\ndifferent scales (e.g. due to perspective effects) which can make it difficult\nfor a learning agent to learn the proper density map. While the use of multiple\ncolumns to extract multiscale information from images has been shown before,\nour approach aggregates the multiscale information gathered by the multicolumn\nconvolutional neural network to improve performance. Our experiments show that\nour proposed network outperforms the state-of-the-art on many benchmark\ndatasets, and also that using our aggregation module in combination with a\nhigher number of columns is beneficial for multiscale counting.","url_abs":"http://arxiv.org/abs/1804.07821v1","url_pdf":"http://arxiv.org/pdf/1804.07821v1.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":"an-aggregated-multicolumn-dilated-convolution","repo_url":"https://github.com/diptodip/counting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"an-aggregated-multicolumn-dilated-convolution","repo_url":"https://github.com/vikparuchuri/marker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.07821","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}