Oxford-IIIT Pets

Introduced by Omkar M. Parkhi et al. in Cats and dogs

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.

Source: https://www.robots.ox.ac.uk/~vgg/data/pets/

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Fine-Grained Image Classification	Oxford-IIIT Pets	EffNet-L2
Image Classification	Oxford-IIIT Pets	CeiT-S
Neural Architecture Search	Oxford-IIIT Pets	NAT-M4
Image Compression	Oxford-IIIT Pets	Lossyless Compressor