{"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/end-to-end-cross-modality-retrieval-with-cca","title":"End-to-End Cross-Modality Retrieval with CCA Projections and Pairwise Ranking Loss","arxiv_id":"1705.06979","date":"2018-04-16","proceeding":null,"authors":["Dorfer Matthias","Schlüter Jan","Vall Andreu","Korzeniowski Filip","Widmer Gerhard"],"abstract":"Cross-modality retrieval encompasses retrieval tasks where the fetched items\nare of a different type than the search query, e.g., retrieving pictures\nrelevant to a given text query. The state-of-the-art approach to cross-modality\nretrieval relies on learning a joint embedding space of the two modalities,\nwhere items from either modality are retrieved using nearest-neighbor search.\nIn this work, we introduce a neural network layer based on Canonical\nCorrelation Analysis (CCA) that learns better embedding spaces by analytically\ncomputing projections that maximize correlation. In contrast to previous\napproaches, the CCA Layer (CCAL) allows us to combine existing objectives for\nembedding space learning, such as pairwise ranking losses, with the optimal\nprojections of CCA. We show the effectiveness of our approach for\ncross-modality retrieval on three different scenarios (text-to-image,\naudio-sheet-music and zero-shot retrieval), surpassing both Deep CCA and a\nmulti-view network using freely learned projections optimized by a pairwise\nranking loss, especially when little training data is available (the code for\nall three methods is released at: https://github.com/CPJKU/cca_layer).","url_abs":"http://arxiv.org/abs/1705.06979v2","url_pdf":"http://arxiv.org/pdf/1705.06979v2.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":"end-to-end-cross-modality-retrieval-with-cca","repo_url":"https://github.com/CPJKU/cca_layer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}