{"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/parallel-grid-pooling-for-data-augmentation","title":"Parallel Grid Pooling for Data Augmentation","arxiv_id":"1803.11370","date":"2018-03-30","proceeding":null,"authors":["Akito Takeki","Daiki Ikami","Go Irie","Kiyoharu Aizawa"],"abstract":"Convolutional neural network (CNN) architectures utilize downsampling layers,\nwhich restrict the subsequent layers to learn spatially invariant features\nwhile reducing computational costs. However, such a downsampling operation\nmakes it impossible to use the full spectrum of input features. Motivated by\nthis observation, we propose a novel layer called parallel grid pooling (PGP)\nwhich is applicable to various CNN models. PGP performs downsampling without\ndiscarding any intermediate feature. It works as data augmentation and is\ncomplementary to commonly used data augmentation techniques. Furthermore, we\ndemonstrate that a dilated convolution can naturally be represented using PGP\noperations, which suggests that the dilated convolution can also be regarded as\na type of data augmentation technique. Experimental results based on popular\nimage classification benchmarks demonstrate the effectiveness of the proposed\nmethod. Code is available at: https://github.com/akitotakeki","url_abs":"http://arxiv.org/abs/1803.11370v1","url_pdf":"http://arxiv.org/pdf/1803.11370v1.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":"parallel-grid-pooling-for-data-augmentation","repo_url":"https://github.com/akitotakeki/pgp-chainer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-augmentation","task_name":"Image Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}