Computer vision models may not be good art critics, but they certainly can be trained to be good art recognizers. In this competition, we ask you to build an object detection model for identifying heads. The twist? None of the heads are real! Rather than photos of real life, each image is a painting, print, or sketch from public domain artwork. 

**This dataset was created by [Scale Rapid](https://scale.com/rapid)**, the fastest annotation platform to help you obtain production-quality labels with no data minimums. We support a wide range of use cases, including classification, transcription, semantic segmentation, polygon image annotations, and more. **To get started, visit [this link](https://scale.com/kaggle) to receive $250 of free labeling credits!**

Each head is at least 50px wide and 50px tall, and labelers were instructed to ignore heads where no part of the face is visible (i.e. only the back of the head is visible to the viewer). Your training data will include bounding box information for all the human heads in the dataset, and for the test set you will be asked to predict the number of human heads without the bounding boxes given to you.

Here is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).


## Acknowledgements

We thank the New York Metropolitan Museum of Art for supplying the original images for this dataset