Oxford-IIIT Pet Dataset

Introduced by ZHANG et al. in 0/1 Deep Neural Networks via Block Coordinate Descent

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/

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Fine-Grained Image Classification	Oxford-IIIT Pet Dataset	DINOv2
Image Classification	Oxford-IIIT Pet Dataset	efficient adaptive ensembling
Neural Architecture Search	Oxford-IIIT Pet Dataset	NAT-M4
Image Compression	Oxford-IIIT Pet Dataset	Lossyless Compressor