Oxford-IIIT Pet Dataset

ImagesCC BY-SA 4.0Introduced 2022-06-19

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

Benchmarks

AutoML/Accuracy (%)AutoML/FLOPS AutoML/PARAMS 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/PARAMS Image Classification/FLOPS Image Classification/Top-1 Error Rate Image Compression/Bit rate Neural Architecture Search/Accuracy (%)Neural Architecture Search/FLOPS Neural Architecture Search/PARAMS Prompt Engineering/Harmonic mean