{"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/an-embarrassingly-simple-approach-to-zero","title":"An embarrassingly simple approach to zero-shot learning","arxiv_id":null,"date":"2015-07-06","proceeding":"Proceedings of the International Conference on International Conference on Machine Learning 2015 7","authors":["Bernardino Romera-Paredes","Philip H. S. Torr"],"abstract":"Zero-shot learning consists in learning how to recognise new concepts by just having a description of them. Many sophisticated approaches have been proposed to address the challenges this problem comprises. In this paper we describe a zero-shot learning approach that can be implemented in just one line of code, yet it is able to outperform state of the art approaches on standard datasets. The approach is based on a more general framework which models the relationships between features, attributes, and classes as a two linear layers network, where the weights of the top layer are not learned but are given by the environment. We further provide a learning bound on the generalisation error of this kind of approaches, by casting them as domain adaptation methods. In experiments carried out on three standard real datasets, we found that our approach is able to perform significantly better than the state of art on all of them, obtaining a ratio of improvement up to 17%.","url_abs":"https://dl.acm.org/doi/10.5555/3045118.3045347","url_pdf":"http://jmlr.org/proceedings/papers/v37/romera-paredes15.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":"an-embarrassingly-simple-approach-to-zero","repo_url":"https://github.com/chichilicious/embarrsingly-simple-zero-shot-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-action-recognition-on-kinetics","task":"Zero-Shot Action Recognition","dataset":"Kinetics","model":"ESZSL","rank_in_archive_order":18,"of":20,"metrics":{"Top-1 Accuracy":"22.9","Top-5 Accuracy":"48.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-olympics","task":"Zero-Shot Action Recognition","dataset":"Olympics","model":"ESZSL","rank_in_archive_order":8,"of":9,"metrics":{"Top-1 Accuracy":"39.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset":"UCF101","model":"ESZSL","rank_in_archive_order":31,"of":35,"metrics":{"Top-1 Accuracy":"15.0"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}