{"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/universal-perceptual-grouping","title":"Universal Perceptual Grouping","arxiv_id":"1808.02312","date":"2018-08-07","proceeding":null,"authors":["Ke Li","Kaiyue Pang","Jifei Song","Yi-Zhe Song","Tao Xiang","Timothy M. Hospedales","Honggang Zhang"],"abstract":"In this work we aim to develop a universal sketch grouper. That is, a grouper\nthat can be applied to sketches of any category in any domain to group\nconstituent strokes/segments into semantically meaningful object parts. The\nfirst obstacle to this goal is the lack of large-scale datasets with grouping\nannotation. To overcome this, we contribute the largest sketch perceptual\ngrouping (SPG) dataset to date, consisting of 20,000 unique sketches evenly\ndistributed over 25 object categories. Furthermore, we propose a novel deep\nuniversal perceptual grouping model. The model is learned with both generative\nand discriminative losses. The generative losses improve the generalisation\nability of the model to unseen object categories and datasets. The\ndiscriminative losses include a local grouping loss and a novel global grouping\nloss to enforce global grouping consistency. We show that the proposed model\nsignificantly outperforms the state-of-the-art groupers. Further, we show that\nour grouper is useful for a number of sketch analysis tasks including sketch\nsynthesis and fine-grained sketch-based image retrieval (FG-SBIR).","url_abs":"http://arxiv.org/abs/1808.02312v1","url_pdf":"http://arxiv.org/pdf/1808.02312v1.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":"universal-perceptual-grouping","repo_url":"https://github.com/KeLi-SketchX/Universal-sketch-perceptual-grouping","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"object","task_name":"Object"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sketch-based-image-retrieval","task_name":"Sketch-Based Image Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1808.02312","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}