The Oxford-IIIT Pet Dataset has 37 categories with roughly 200 images for each class. The images have a large variations in scale, pose and lighting. All images have an associated ground truth annotation of breed, head ROI, and pixel level trimap segmentation.
Also available on Academic torrent, Link is here
Source: https://www.robots.ox.ac.uk/~vgg/data/pets/Paper | Code | Results | Date | Stars |
---|