{"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/image-similarity-using-deep-cnn-and","title":"Image similarity using Deep CNN and Curriculum Learning","arxiv_id":"1709.08761","date":"2017-09-26","proceeding":null,"authors":["Srikar Appalaraju","Vineet Chaoji"],"abstract":"Image similarity involves fetching similar looking images given a reference\nimage. Our solution called SimNet, is a deep siamese network which is trained\non pairs of positive and negative images using a novel online pair mining\nstrategy inspired by Curriculum learning. We also created a multi-scale CNN,\nwhere the final image embedding is a joint representation of top as well as\nlower layer embedding's. We go on to show that this multi-scale siamese network\nis better at capturing fine grained image similarities than traditional CNN's.","url_abs":"http://arxiv.org/abs/1709.08761v2","url_pdf":"http://arxiv.org/pdf/1709.08761v2.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":"image-similarity-using-deep-cnn-and","repo_url":"https://github.com/sardnet/image_comparison","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"siamese-network","method_name":"Siamese Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.08761","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}