{"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/one-shot-texture-segmentation","title":"One-shot Texture Segmentation","arxiv_id":"1807.02654","date":"2018-07-07","proceeding":null,"authors":["Ivan Ustyuzhaninov","Claudio Michaelis","Wieland Brendel","Matthias Bethge"],"abstract":"We introduce one-shot texture segmentation: the task of segmenting an input\nimage containing multiple textures given a patch of a reference texture. This\ntask is designed to turn the problem of texture-based perceptual grouping into\nan objective benchmark. We show that it is straight-forward to generate large\nsynthetic data sets for this task from a relatively small number of natural\ntextures. In particular, this task can be cast as a self-supervised problem\nthereby alleviating the need for massive amounts of manually annotated data\nnecessary for traditional segmentation tasks. In this paper we introduce and\nstudy two concrete data sets: a dense collage of textures (CollTex) and a\ncluttered texturized Omniglot data set. We show that a baseline model trained\non these synthesized data is able to generalize to natural images and videos\nwithout further fine-tuning, suggesting that the learned image representations\nare useful for higher-level vision tasks.","url_abs":"http://arxiv.org/abs/1807.02654v1","url_pdf":"http://arxiv.org/pdf/1807.02654v1.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":"one-shot-texture-segmentation","repo_url":"https://github.com/ivust/one-shot-texture-segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"one-shot-texture-segmentation","repo_url":"https://github.com/LiamLYJ/scene_seg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"one-shot-texture-segmentation","repo_url":"https://github.com/atch841/one-shot-texture-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"one-shot-texture-segmentation","repo_url":"https://github.com/drogen120/OneshotTextureSegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.02654","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}