Datasets › AwA
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/
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Long-tail learning with class descriptors | AWA-LT | DRAGON + Bal'Loss Per-Class Accuracy 76.2 | From Generalized zero-shot learning to long-tail with... | dvirsamuel/DRAGON | 5 | Compare |
| Few-Shot Image Classification | AWA - 0-Shot | Synthesised Classifier Accuracy 72.9% | Synthesized Classifiers for Zero-Shot Learning | JudyYe/zero-shot-gcn +1 | 1 | Compare |
| Few-Shot Image Classification | AWA1 - 0-Shot | TAFE-Net Accuracy 70.8 | TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning | ucbdrive/tafe-net | 1 | Compare |
Papers archive 2025-07-28
6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 264. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| From Generalized zero-shot learning to long-tail with class descriptors | 1 | 2 | 5 Apr 2020 | not harvested |
| Decoupling Representation and Classifier for Long-Tailed Recognition | 4 | 1 | 21 Oct 2019 | ran 2 of 2 samples (0 unverified; 2 pointer-only for licence) |
| Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss | 7 | 1 | 18 Jun 2019 | ran 2 of 11 samples (9 unverified; 3 pointer-only for licence) |
| Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders | 1 | 1 | 1 Jun 2019 | not harvested |
| TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning | 1 | 1 | 11 Apr 2019 | ran 1 of 3 samples (2 unverified) |
| Synthesized Classifiers for Zero-Shot Learning | 2 | 1 | 2 Mar 2016 | ran 0 of 3 samples (3 unverified; 2 pointer-only for licence) |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Unknown
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- AWA - 0-Shot
- AWA1 - 0-Shot
- AWA-LT
- AwA2
- AwA
5 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections