The Metropolitan Museum of Art in New York, also known as The Met, has a diverse collection of over 1.5M objects of which over 200K have been digitized with imagery. The online cataloguing information is generated by Subject Matter Experts (SME) and includes a wide range of data. These include, but are not limited to: multiple object classifications, artist, title, period, date, medium, culture, size, provenance, geographic location, and other related museum objects within The Met’s collection. While the SME-generated annotations describe the object from an art history perspective, they can also be indirect in describing finer-grained attributes from the museum-goer’s understanding. Adding fine-grained attributes to aid in the visual understanding of the museum objects will enable the ability to search for visually related objects.
We present The Met’s digitized and annotated collection as a multi-attribute FGVCx challenge for CVPR 2018.
Multiple modalities can be expected and the camera sources are unknown. The photographs are often centered for objects, and in the case where the museum artifact is an entire room, the images are scenic in nature.
Each object is seen by a single worker without a verification step. Workers are advised to add multiple labels from an ontology provided by The Met, and additionally are allowed to add free-form text when they see fit. The crowd is able to view the museum’s online collection pages and is advised to avoid annotating labels already present. Specifically, the crowd is advised to annotate labels related to what they “see” or what they infer as the object’s “utility.” We consider these annotations noisy.
Each data sample contains one image and at least one attribute label from a label set of 1103 attributes. The dimension of each image is normalized such that the shorter dimension is 300 pixels.
109,274 Samples
7,443 Samples
38,814 Samples
F_beta-score on the test set will be used as final score.
This is an FGVCx competition as part of the FGVC^6 workshop at CVPR 2019.
We are using Kaggle to host the leaderboard. Competition link: https://www.kaggle.com/c/imet-2019-fgvc6
| Competition Starts | March, 2019 |
| Submission Deadline | June 4, 2019 |