{"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/dilated-residual-networks","title":"Dilated Residual Networks","arxiv_id":"1705.09914","date":"2017-05-28","proceeding":"CVPR 2017 7","authors":["Fisher Yu","Vladlen Koltun","Thomas Funkhouser"],"abstract":"Convolutional networks for image classification progressively reduce\nresolution until the image is represented by tiny feature maps in which the\nspatial structure of the scene is no longer discernible. Such loss of spatial\nacuity can limit image classification accuracy and complicate the transfer of\nthe model to downstream applications that require detailed scene understanding.\nThese problems can be alleviated by dilation, which increases the resolution of\noutput feature maps without reducing the receptive field of individual neurons.\nWe show that dilated residual networks (DRNs) outperform their non-dilated\ncounterparts in image classification without increasing the model's depth or\ncomplexity. We then study gridding artifacts introduced by dilation, develop an\napproach to removing these artifacts (`degridding'), and show that this further\nincreases the performance of DRNs. In addition, we show that the accuracy\nadvantage of DRNs is further magnified in downstream applications such as\nobject localization and semantic segmentation.","url_abs":"http://arxiv.org/abs/1705.09914v1","url_pdf":"http://arxiv.org/pdf/1705.09914v1.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":"dilated-residual-networks","repo_url":"https://github.com/fyu/drn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dilated-residual-networks","repo_url":"https://github.com/cj-mclaughlin/segmentation_research","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dilated-residual-networks","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"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-localization","task_name":"Object Localization"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.09914","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}