AwA2 (Animals with Attributes 2)

Introduced by Xian et al. in Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly

Animals with Attributes 2 (AwA2) is a dataset for benchmarking transfer-learning algorithms, such as attribute base classification and zero-shot learning. AwA2 is a drop-in replacement of original Animals with Attributes (AwA) dataset, with more images released for each category. Specifically, AwA2 consists of in total 37322 images distributed in 50 animal categories. The AwA2 also provides a category-attribute matrix, which contains an 85-dim attribute vector (e.g., color, stripe, furry, size, and habitat) for each category.

Source: Learning from Noisy Web Data with Category-level Supervision

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Generalized Few-Shot Learning	AwA2	MVCN
Zero-Shot Learning	AwA2	ZSL-KG
Generalized Zero-Shot Learning	AwA2	ZSL-KG
Few-Shot Image Classification	AWA2 - 0-Shot	TAFE-Net