{"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/core50-a-new-dataset-and-benchmark-for","title":"CORe50: a New Dataset and Benchmark for Continuous Object Recognition","arxiv_id":"1705.03550","date":"2017-05-09","proceeding":null,"authors":["Vincenzo Lomonaco","Davide Maltoni"],"abstract":"Continuous/Lifelong learning of high-dimensional data streams is a\nchallenging research problem. In fact, fully retraining models each time new\ndata become available is infeasible, due to computational and storage issues,\nwhile na\\\"ive incremental strategies have been shown to suffer from\ncatastrophic forgetting. In the context of real-world object recognition\napplications (e.g., robotic vision), where continuous learning is crucial, very\nfew datasets and benchmarks are available to evaluate and compare emerging\ntechniques. In this work we propose a new dataset and benchmark CORe50,\nspecifically designed for continuous object recognition, and introduce baseline\napproaches for different continuous learning scenarios.","url_abs":"http://arxiv.org/abs/1705.03550v1","url_pdf":"http://arxiv.org/pdf/1705.03550v1.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":"core50-a-new-dataset-and-benchmark-for","repo_url":"https://github.com/lifelong-robotic-vision/lifelong-object-recognition-challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continuous-object-recognition","task_name":"Continuous Object Recognition"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[{"slug":"core50","name":"CORe50","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.03550","atlas_url":"https://app.syntology.ai/?focus=1705.03550","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}