Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟵𝟴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗧𝗵𝗲 𝗠𝗲𝘁 𝗗𝗮𝘁𝗮𝘀𝗲𝘁: 𝗜𝗻𝘀𝘁𝗮𝗻𝗰𝗲-𝗹𝗲𝘃𝗲𝗹 𝗥𝗲𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝗼𝗻 for the Artwork 𝗯𝘆 University of Amsterdam, Osaka University Czech Technical University in Prague and Columbia university Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: The Met Dataset: Instance-level Recognition for Artworks 🔸 This paper is published arxiv2022. 🔸 The Met dataset is a large-scale dataset for Instance-Level Recognition (ILR) in the artwork domain. This relies on the open-access collection from the Metropolitan Museum of Art (The Met) in New York to form the training set, which consists of about 400k images from more than 224k classes, with artworks of world-level geographic coverage and chronological periods dating back to the Paleolithic period. Each museum exhibit corresponds to unique artwork and defines its own class. The training set exhibits a long-tail distribution with more than half of the classes represented by a single image, making it a special case of few-shot learning. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 This work introduces a dataset for large-scale instance-level recognition in the domain of artworks. The proposed benchmark exhibits a number of different challenges such as large inter-class similarity, long-tail distribution, and many classes.  🔸 It relies on the open-access collection of The Met museum to form a large training set of about 224k classes, where each class corresponds to a museum exhibit with photos taken under studio conditions.  🔸 Testing is primarily performed on photos taken by museum guests depicting exhibits, which introduces a distribution shift between training and testing.  🔸 Testing is additionally performed on a set of images not related to Met exhibits making the task resemble an out-of-distribution detection problem.  🔸 The proposed benchmark follows the paradigm of other recent datasets for instance-level recognition on different domains to encourage research on domain-independent approaches.  🔸 A number of suitable approaches are evaluated to offer a testbed for future comparisons. Self-supervised and supervised contrastive learning are effectively combined to train the backbone which is used for non-parametric classification that is shown as a promising direction.  #computervision #artificialintelligence #technology