{"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/hashing-as-tie-aware-learning-to-rank","title":"Hashing as Tie-Aware Learning to Rank","arxiv_id":"1705.08562","date":"2017-05-23","proceeding":"CVPR 2018 6","authors":["Kun He","Fatih Cakir","Sarah Adel Bargal","Stan Sclaroff"],"abstract":"Hashing, or learning binary embeddings of data, is frequently used in nearest\nneighbor retrieval. In this paper, we develop learning to rank formulations for\nhashing, aimed at directly optimizing ranking-based evaluation metrics such as\nAverage Precision (AP) and Normalized Discounted Cumulative Gain (NDCG). We\nfirst observe that the integer-valued Hamming distance often leads to tied\nrankings, and propose to use tie-aware versions of AP and NDCG to evaluate\nhashing for retrieval. Then, to optimize tie-aware ranking metrics, we derive\ntheir continuous relaxations, and perform gradient-based optimization with deep\nneural networks. Our results establish the new state-of-the-art for image\nretrieval by Hamming ranking in common benchmarks.","url_abs":"http://arxiv.org/abs/1705.08562v4","url_pdf":"http://arxiv.org/pdf/1705.08562v4.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":"hashing-as-tie-aware-learning-to-rank","repo_url":"https://github.com/kunhe/TALR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.08562","atlas_url":"https://app.syntology.ai/?focus=1705.08562","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}