{"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/graph-rise-graph-regularized-image-semantic","title":"Graph-RISE: Graph-Regularized Image Semantic Embedding","arxiv_id":"1902.10814","date":"2019-02-14","proceeding":null,"authors":["Da-Cheng Juan","Chun-Ta Lu","Zhen Li","Futang Peng","Aleksei Timofeev","Yi-Ting Chen","Yaxi Gao","Tom Duerig","Andrew Tomkins","Sujith Ravi"],"abstract":"Learning image representations to capture fine-grained semantics has been a\nchallenging and important task enabling many applications such as image search\nand clustering. In this paper, we present Graph-Regularized Image Semantic\nEmbedding (Graph-RISE), a large-scale neural graph learning framework that\nallows us to train embeddings to discriminate an unprecedented O(40M)\nultra-fine-grained semantic labels. Graph-RISE outperforms state-of-the-art\nimage embedding algorithms on several evaluation tasks, including image\nclassification and triplet ranking. We provide case studies to demonstrate\nthat, qualitatively, image retrieval based on Graph-RISE effectively captures\nsemantics and, compared to the state-of-the-art, differentiates nuances at\nlevels that are closer to human-perception.","url_abs":"http://arxiv.org/abs/1902.10814v1","url_pdf":"http://arxiv.org/pdf/1902.10814v1.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":"graph-rise-graph-regularized-image-semantic","repo_url":"https://github.com/tensorflow/neural-structured-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"k-nn","method_name":"k-NN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Graph-RISE (40M)","rank_in_archive_order":1034,"of":1060,"metrics":{"Top 1 Accuracy":"68.29%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset":"iNaturalist","model":"Graph-RISE (40M)","rank_in_archive_order":17,"of":19,"metrics":{"Top 1 Accuracy":"31.12%","Top 5 Accuracy":"52.76%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.10814","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}