{"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/retrieving-similar-e-commerce-images-using","title":"Retrieving Similar E-Commerce Images Using Deep Learning","arxiv_id":"1901.03546","date":"2019-01-11","proceeding":null,"authors":["Rishab Sharma","Anirudha Vishvakarma"],"abstract":"In this paper, we propose a deep convolutional neural network for learning\nthe embeddings of images in order to capture the notion of visual similarity.\nWe present a deep siamese architecture that when trained on positive and\nnegative pairs of images learn an embedding that accurately approximates the\nranking of images in order of visual similarity notion. We also implement a\nnovel loss calculation method using an angular loss metrics based on the\nproblems requirement. The final embedding of the image is combined\nrepresentation of the lower and top-level embeddings. We used fractional\ndistance matrix to calculate the distance between the learned embeddings in\nn-dimensional space. In the end, we compare our architecture with other\nexisting deep architecture and go on to demonstrate the superiority of our\nsolution in terms of image retrieval by testing the architecture on four\ndatasets. We also show how our suggested network is better than the other\ntraditional deep CNNs used for capturing fine-grained image similarities by\nlearning an optimum embedding.","url_abs":"http://arxiv.org/abs/1901.03546v1","url_pdf":"http://arxiv.org/pdf/1901.03546v1.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":"retrieving-similar-e-commerce-images-using","repo_url":"https://github.com/Ducvoccer/mildnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"retrieving-similar-e-commerce-images-using","repo_url":"https://github.com/gofynd/mildnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"retrieving-similar-e-commerce-images-using","repo_url":"https://github.com/khatria/Retrieving-Similar-E-Commerce-Images-Using-Deep-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"fine-grained-visual-recognition","task_name":"Fine-Grained Visual Recognition"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"product-recommendation","task_name":"Product Recommendation"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-street2shop-topwear","task":"Image Retrieval","dataset":"street2shop - topwear","model":"Ranknet","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"94.98"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.03546","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}