visipedia/imet-fgvcx

iMet Collection - FGVCx 2019 Challenge @ FGVC6, CVPR 2019

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.

iMet Collection - FGVCx competition based on The Met's digitized collection

We present The Met’s digitized and annotated collection as a multi-attribute FGVCx challenge for CVPR 2018.

Images

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.

Annotations

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.

Data sets

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.

Training set

109,274 Samples

Validation set

7,443 Samples

Test set

38,814 Samples

Metric

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.

Competition Platform

We are using Kaggle to host the leaderboard. Competition link: https://www.kaggle.com/c/imet-2019-fgvc6

Dates

Competition Starts	March, 2019
Submission Deadline	June 4, 2019

imet-fgvcx's Issues

Late submission is unavailable

Hi!

I am not able to submit my results even I have already joined this competition. You can find the details of problems on the Kaggle discussion thread here. Thank you!

https://www.kaggle.com/c/imet-2019-fgvc6/discussion/96890#latest-693460