{"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/museum-exhibit-identification-challenge-for","title":"Museum Exhibit Identification Challenge for Domain Adaptation and Beyond","arxiv_id":"1802.01093","date":"2018-02-04","proceeding":null,"authors":["Piotr Koniusz","Yusuf Tas","Hongguang Zhang","Mehrtash Harandi","Fatih Porikli","Rui Zhang"],"abstract":"In this paper, we approach an open problem of artwork identification and\npropose a new dataset dubbed Open Museum Identification Challenge (Open MIC).\nIt contains photos of exhibits captured in 10 distinct exhibition spaces of\nseveral museums which showcase paintings, timepieces, sculptures, glassware,\nrelics, science exhibits, natural history pieces, ceramics, pottery, tools and\nindigenous crafts. The goal of Open MIC is to stimulate research in domain\nadaptation, egocentric recognition and few-shot learning by providing a testbed\ncomplementary to the famous Office dataset which reaches 90% accuracy. To form\nour dataset, we captured a number of images per art piece with a mobile phone\nand wearable cameras to form the source and target data splits, respectively.\nTo achieve robust baselines, we build on a recent approach that aligns\nper-class scatter matrices of the source and target CNN streams [15]. Moreover,\nwe exploit the positive definite nature of such representations by using\nend-to-end Bregman divergences and the Riemannian metric. We present baselines\nsuch as training/evaluation per exhibition and training/evaluation on the\ncombined set covering 866 exhibit identities. As each exhibition poses distinct\nchallenges e.g., quality of lighting, motion blur, occlusions, clutter,\nviewpoint and scale variations, rotations, glares, transparency, non-planarity,\nclipping, we break down results w.r.t. these factors.","url_abs":"http://arxiv.org/abs/1802.01093v1","url_pdf":"http://arxiv.org/pdf/1802.01093v1.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":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[],"datasets_introduced":[{"slug":"open-mic","name":"Open MIC","full_name":"Open Museum Identification Challenge"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}