Oxford-IIIT Pets

The Oxford-IIIT Pet Dataset is a 37-category pet dataset with roughly 200 images for each class. The images have large variations in scale, pose, and lighting. All images have an associated ground truth annotation of breed, head ROI, and pixel-level trimap segmentation.

Benchmarks

Fine-Grained Image Classification/Accuracy Fine-Grained Image Classification/Top-1 Error Rate Fine-Grained Image Classification/FLOPS Fine-Grained Image Classification/PARAMS Image Classification/Accuracy Image Classification/Per-Class Accuracy Image Classification/Top-1 Error Rate Image Classification/FLOPS Image Classification/PARAMS Image Clustering/Accuracy Zero-Shot Learning/Accuracy