{"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/weakly-and-self-supervised-learning-for","title":"Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting","arxiv_id":"1708.02731","date":"2017-08-09","proceeding":"ICCV 2017 10","authors":["Donghyeon Cho","Jinsun Park","Tae-Hyun Oh","Yu-Wing Tai","In So Kweon"],"abstract":"This paper proposes a weakly- and self-supervised deep convolutional neural\nnetwork (WSSDCNN) for content-aware image retargeting. Our network takes a\nsource image and a target aspect ratio, and then directly outputs a retargeted\nimage. Retargeting is performed through a shift map, which is a pixel-wise\nmapping from the source to the target grid. Our method implicitly learns an\nattention map, which leads to a content-aware shift map for image retargeting.\nAs a result, discriminative parts in an image are preserved, while background\nregions are adjusted seamlessly. In the training phase, pairs of an image and\nits image-level annotation are used to compute content and structure losses. We\ndemonstrate the effectiveness of our proposed method for a retargeting\napplication with insightful analyses.","url_abs":"http://arxiv.org/abs/1708.02731v1","url_pdf":"http://arxiv.org/pdf/1708.02731v1.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":"weakly-and-self-supervised-learning-for","repo_url":"https://github.com/harora/Content-Aware-Image-Retargeting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"weakly-and-self-supervised-learning-for","repo_url":"https://github.com/linchuming/WSSDCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-retargeting","task_name":"Image Retargeting"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.02731","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}