{"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/apac-augmented-pattern-classification-with","title":"APAC: Augmented PAttern Classification with Neural Networks","arxiv_id":"1505.03229","date":"2015-05-13","proceeding":null,"authors":["Ikuro Sato","Hiroki Nishimura","Kensuke Yokoi"],"abstract":"Deep neural networks have been exhibiting splendid accuracies in many of\nvisual pattern classification problems. Many of the state-of-the-art methods\nemploy a technique known as data augmentation at the training stage. This paper\naddresses an issue of decision rule for classifiers trained with augmented\ndata. Our method is named as APAC: the Augmented PAttern Classification, which\nis a way of classification using the optimal decision rule for augmented data\nlearning. Discussion of methods of data augmentation is not our primary focus.\nWe show clear evidences that APAC gives far better generalization performance\nthan the traditional way of class prediction in several experiments. Our\nconvolutional neural network model with APAC achieved a state-of-the-art\naccuracy on the MNIST dataset among non-ensemble classifiers. Even our\nmultilayer perceptron model beats some of the convolutional models with\nrecently invented stochastic regularization techniques on the CIFAR-10 dataset.","url_abs":"http://arxiv.org/abs/1505.03229v1","url_pdf":"http://arxiv.org/pdf/1505.03229v1.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"APAC","rank_in_archive_order":208,"of":265,"metrics":{"Percentage correct":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"APAC","rank_in_archive_order":9,"of":81,"metrics":{"Percentage error":"0.23"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.03229","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}