AwA

Animals with Attributes

Animals with Attributes (AwA) was a dataset for benchmarking transfer-learning algorithms, in particular attribute base classification. It consisted of 30475 images of 50 animals classes with six pre-extracted feature representations for each image. The animals classes are aligned with Osherson's classical class/attribute matrix, thereby providing 85 numeric attribute values for each class. Using the shared attributes, it is possible to transfer information between different classes. The Animals with Attributes dataset was suspended. Its images are not available anymore because of copyright restrictions. A drop-in replacement, Animals with Attributes 2, is available instead. Source: Transductive Multi-view Zero-Shot Learning Image Source: https://cvml.ist.ac.at/AwA/

Images

벤치마크

Long-tail learning with class descriptors on AWA-LT 결과 25개

Generalized Few-Shot Learning on AwA2 결과 6개

Concept-based Classification on AwA2 결과 4개

Generalized Zero-Shot Learning on AwA2 결과 4개

Zero-Shot Learning on AwA2 결과 4개

Few-Shot Image Classification on AWA - 0-Shot 결과 2개

Few-Shot Image Classification on AWA1 - 0-Shot 결과 2개