The Met Dataset
Met

What is the Met dataset?


The Met dataset is a large-scale dataset for Instance-Level Recognition (ILR) in the artwork domain.

Evaluation


Recognition performance on the test set (queries) of the Met Dataset is measured with average classification accuracy (ACC) on the Met queries, and with Global Average Precision (GAP) on all queries.

Downloads

Dataset


The images of the dataset and the ground-truth files can be downloaded from the links below. All images have been resized so that their largest side is 500 pixels.

Embedding models


Models for descriptor extraction can be downloaded from the links below. They can be used directly to extract descriptors with the provided code for descriptor extraction.

Descriptors


Descriptors extracted using the models above can be downloaded from the links below. They can be used directly with the provided code for kNN classification.

Code


Code is provided on github to offer support for:

Presentation


A video of the presentation of the Met Dataset at the 4th Instance-Level Recognition Workshop of ICCV'21 can be found here.

Related publication


The Met Dataset: Instance-level Recognition for Artworks [ pdf | suppl | bib | poster | video ]
N.A. Ypsilantis, N. Garcia, G. Han, S. Ibrahimi, N. van Noord, G. Tolias
Accepted at NeurIPS 2021 Track on Datasets and Benchmarks.

Feedback

Any feedback is very welcome. Please send it to: ypsilnik@fel.cvut.cz