{"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/learning-to-learn-from-web-data-through-deep","title":"Learning to Learn from Web Data through Deep Semantic Embeddings","arxiv_id":"1808.06368","date":"2018-08-20","proceeding":null,"authors":["Raul Gomez","Lluis Gomez","Jaume Gibert","Dimosthenis Karatzas"],"abstract":"In this paper we propose to learn a multimodal image and text embedding from\nWeb and Social Media data, aiming to leverage the semantic knowledge learnt in\nthe text domain and transfer it to a visual model for semantic image retrieval.\nWe demonstrate that the pipeline can learn from images with associated text\nwithout supervision and perform a thourough analysis of five different text\nembeddings in three different benchmarks. We show that the embeddings learnt\nwith Web and Social Media data have competitive performances over supervised\nmethods in the text based image retrieval task, and we clearly outperform state\nof the art in the MIRFlickr dataset when training in the target data. Further\nwe demonstrate how semantic multimodal image retrieval can be performed using\nthe learnt embeddings, going beyond classical instance-level retrieval\nproblems. Finally, we present a new dataset, InstaCities1M, composed by\nInstagram images and their associated texts that can be used for fair\ncomparison of image-text embeddings.","url_abs":"http://arxiv.org/abs/1808.06368v1","url_pdf":"http://arxiv.org/pdf/1808.06368v1.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":"learning-to-learn-from-web-data-through-deep","repo_url":"https://github.com/gombru/LearnFromWebData","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"instacities1m","name":"InstaCities1M","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.06368","atlas_url":"https://app.syntology.ai/?focus=1808.06368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}