{"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/sketch-me-that-shoe","title":"Sketch Me That Shoe","arxiv_id":null,"date":"2016-06-01","proceeding":"CVPR 2016 6","authors":["Qian Yu","Feng Liu","Yi-Zhe Song","Tao Xiang","Timothy M. Hospedales","Chen-Change Loy"],"abstract":"We investigate the problem of fine-grained sketch-based image retrieval (SBIR), where free-hand human sketches are used as queries to perform instance-level retrieval of images. This is an extremely challenging task because (i) visual comparisons not only need to be fine-grained but also executed cross-domain, (ii) free-hand (finger) sketches are highly abstract, making fine-grained matching harder, and most importantly (iii) annotated cross-domain sketch-photo datasets required for training are scarce, challenging many state-of-the-art machine learning techniques.     In this paper, for the first time, we address all these challenges, providing a step towards the capabilities that would underpin a commercial sketch-based image retrieval application. We introduce a new database of 1,432 sketch-photo pairs from two categories with 32,000 fine-grained triplet ranking annotations. We then develop a deep triplet-ranking model for instance-level SBIR with a novel data augmentation and staged pre-training strategy to alleviate the issue of insufficient fine-grained training data. Extensive experiments are carried out to contribute a variety of insights into the challenges of data sufficiency and over-fitting avoidance when training deep networks for fine-grained cross-domain ranking tasks. ","url_abs":"http://openaccess.thecvf.com/content_cvpr_2016/html/Yu_Sketch_Me_That_CVPR_2016_paper.html","url_pdf":"http://openaccess.thecvf.com/content_cvpr_2016/papers/Yu_Sketch_Me_That_CVPR_2016_paper.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":[],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sketch-based-image-retrieval","task_name":"Sketch-Based Image Retrieval"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[{"slug":"sketch-me-that-shoe","name":"ShoeV2","full_name":"ShoeV2"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/sketch-based-image-retrieval-on-chairs","task":"Sketch-Based Image Retrieval","dataset":"Chairs","model":"Chairs net +","rank_in_archive_order":3,"of":8,"metrics":{"R@1":"72.2","R@10":"99.0"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-chairs","task":"Sketch-Based Image Retrieval","dataset":"Chairs","model":"Shoes net +","rank_in_archive_order":4,"of":8,"metrics":{"R@1":"65.0","R@10":"92.8"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-chairs","task":"Sketch-Based Image Retrieval","dataset":"Chairs","model":"Dense-HOG + rankSVM","rank_in_archive_order":6,"of":8,"metrics":{"R@1":"52.6","R@10":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-chairs","task":"Sketch-Based Image Retrieval","dataset":"Chairs","model":"Sketch-a-Net + rankSVM","rank_in_archive_order":7,"of":8,"metrics":{"R@1":"47.4","R@10":"82.5"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-chairs","task":"Sketch-Based Image Retrieval","dataset":"Chairs","model":"BoW-HOG + rankSVM","rank_in_archive_order":8,"of":8,"metrics":{"R@1":"28.9","R@10":"67.0"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-handbags","task":"Sketch-Based Image Retrieval","dataset":"Handbags","model":"Chairs net +","rank_in_archive_order":4,"of":8,"metrics":{"R@1":"26.2","R@10":"58.3"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-handbags","task":"Sketch-Based Image Retrieval","dataset":"Handbags","model":"Shoes net +","rank_in_archive_order":5,"of":8,"metrics":{"R@1":"23.2","R@10":"59.5"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-handbags","task":"Sketch-Based Image Retrieval","dataset":"Handbags","model":"Dense-HOG + rankSVM","rank_in_archive_order":6,"of":8,"metrics":{"R@1":"15.5","R@10":"40.5"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-handbags","task":"Sketch-Based Image Retrieval","dataset":"Handbags","model":"Sketch-a-Net + rankSVM","rank_in_archive_order":7,"of":8,"metrics":{"R@1":"9.5","R@10":"44.1"},"uses_additional_data":false},{"leaderboard":"/sota/sketch-based-image-retrieval-on-handbags","task":"Sketch-Based Image Retrieval","dataset":"Handbags","model":"BoW-HOG + rankSVM","rank_in_archive_order":8,"of":8,"metrics":{"R@1":"2.4","R@10":"10.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}