Datasets › AwA2

AwA2 (Animals with Attributes 2)

Introduced by Yongqin Xian et al. in Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly1 Jan 2019 archive 2025-07-28

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 Image Source: https://arxiv.org/pdf/1604.00326.pdf

Benchmarks archive 2025-07-28

All 5 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.

Papers archive 2025-07-28

papers with a benchmark row: 13 · with a code link: 10 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (3 of 13 with a benchmark row: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 13 of 13 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 231. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors 0 1 22 Sep 2024 not harvested
Concept Graph Embedding Models for Enhanced Accuracy and Interpretability 1 1 13 Aug 2024 not harvested
Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models 0 2 5 Jun 2024 not harvested
Better Generalized Few-Shot Learning Even Without Base Data 1 1 29 Nov 2022 not harvested
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning 2 1 4 Jul 2022 not harvested
Zero-Shot Logit Adjustment 1 1 25 Apr 2022 not harvested
Zero-Shot Learning with Common Sense Knowledge Graphs 3 2 18 Jun 2020 not harvested
From Generalized zero-shot learning to long-tail with class descriptors 1 1 5 Apr 2020 not harvested
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification 1 2 17 Mar 2020 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders 1 2 1 Jun 2019 not harvested
TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning 1 1 11 Apr 2019 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders 2 1 5 Dec 2018 official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Learning Robust Visual-Semantic Embeddings 0 1 17 Mar 2017 not harvested

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • AWA2 - 0-Shot
  • AwA2

2 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