{"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/classsim-similarity-between-classes-defined","title":"ClassSim: Similarity between Classes Defined by Misclassification Ratios of Trained Classifiers","arxiv_id":"1802.01267","date":"2018-02-05","proceeding":null,"authors":["Kazuma Arino","Yohei Kikuta"],"abstract":"Deep neural networks (DNNs) have achieved exceptional performances in many\ntasks, particularly, in supervised classification tasks. However, achievements\nwith supervised classification tasks are based on large datasets with\nwell-separated classes. Typically, real-world applications involve wild\ndatasets that include similar classes; thus, evaluating similarities between\nclasses and understanding relations among classes are important. To address\nthis issue, a similarity metric, ClassSim, based on the misclassification\nratios of trained DNNs is proposed herein. We conducted image recognition\nexperiments to demonstrate that the proposed method provides better\nsimilarities compared with existing methods and is useful for classification\nproblems. Source code including all experimental results is available at\nhttps://github.com/karino2/ClassSim/.","url_abs":"http://arxiv.org/abs/1802.01267v1","url_pdf":"http://arxiv.org/pdf/1802.01267v1.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":"classsim-similarity-between-classes-defined","repo_url":"https://github.com/karino2/ClassSim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}