6 datasets found

The Animals with Attributes (AwA) dataset consists of 50 classes of animals, with 30,475 images in total.

The dataset used in the paper is a hierarchical concept representation task, where the goal is to predict is-a relationships between concepts.

The dataset used is Animals with Attributes 2.

The AWA2 dataset includes 50 classes of assorted animals totaling 37,322 samples, of which 10 categories are considered unseen classes. Attribute annotations are 85-dimensional.

The DeformingThings4D-Animals dataset contains 300 meshes from 9 different animal identities, spanning diverse species such as bears, rabbits, dogs, and moose.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...