{"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/some-improvements-on-deep-convolutional","title":"Some Improvements on Deep Convolutional Neural Network Based Image Classification","arxiv_id":"1312.5402","date":"2013-12-19","proceeding":null,"authors":["Andrew G. Howard"],"abstract":"We investigate multiple techniques to improve upon the current state of the\nart deep convolutional neural network based image classification pipeline. The\ntechiques include adding more image transformations to training data, adding\nmore transformations to generate additional predictions at test time and using\ncomplementary models applied to higher resolution images. This paper summarizes\nour entry in the Imagenet Large Scale Visual Recognition Challenge 2013. Our\nsystem achieved a top 5 classification error rate of 13.55% using no external\ndata which is over a 20% relative improvement on the previous year's winner.","url_abs":"http://arxiv.org/abs/1312.5402v1","url_pdf":"http://arxiv.org/pdf/1312.5402v1.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":"some-improvements-on-deep-convolutional","repo_url":"https://github.com/facebook/fb.resnet.torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"some-improvements-on-deep-convolutional","repo_url":"https://github.com/facebookarchive/fb.resnet.torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"some-improvements-on-deep-convolutional","repo_url":"https://github.com/microsoft/fb.resnet.torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"step-decay","method_name":"Step Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1312.5402","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}