{"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/unsupervised-image-to-sequence-translation","title":"Unsupervised Image to Sequence Translation with Canvas-Drawer Networks","arxiv_id":"1809.08340","date":"2018-09-21","proceeding":null,"authors":["Kevin Frans","Chin-Yi Cheng"],"abstract":"Encoding images as a series of high-level constructs, such as brush strokes\nor discrete shapes, can often be key to both human and machine understanding.\nIn many cases, however, data is only available in pixel form. We present a\nmethod for generating images directly in a high-level domain (e.g. brush\nstrokes), without the need for real pairwise data. Specifically, we train a\n\"canvas\" network to imitate the mapping of high-level constructs to pixels,\nfollowed by a high-level \"drawing\" network which is optimized through this\nmapping towards solving a desired image recreation or translation task. We\nsuccessfully discover sequential vector representations of symbols, large\nsketches, and 3D objects, utilizing only pixel data. We display applications of\nour method in image segmentation, and present several ablation studies\ncomparing various configurations.","url_abs":"http://arxiv.org/abs/1809.08340v2","url_pdf":"http://arxiv.org/pdf/1809.08340v2.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":"unsupervised-image-to-sequence-translation","repo_url":"https://github.com/wgoldie/canvasdrawer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.08340","atlas_url":"https://app.syntology.ai/?focus=1809.08340","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}