</> Code with Papers by Syntology

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

HomepageBenchmarksPapers JSON

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.

First row (archive order)PaperCode
Generalized Few-Shot Learning AwA2 MVCN Per-Class Accuracy (1-shot) 69.9 Better Generalized Few-Shot Learning Even Without Base Data bigdata-inha/zero-base-gfsl 6 Compare
Generalized Zero-Shot Learning AwA2 ZeroDiff Harmonic mean 79.5 Exploring Data Efficiency in Zero-Shot Learning with... — 4 Compare
Zero-Shot Learning AwA2 ZeroDiff average top-1 classification accuracy 86.4 Exploring Data Efficiency in Zero-Shot Learning with... — 4 Compare
Concept-based Classification AwA2 EQ-CBM (ResNet-34) Task Accuracy (%) 95.965 EQ-CBM: A Probabilistic Concept Bottleneck with... — 2 Compare
Few-Shot Image Classification AWA2 - 0-Shot TAFE-Net Accuracy 69.3 TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning ucbdrive/tafe-net 1 Compare

Papers archive 2025-07-28

13 shown of 13 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 231. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples 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 ran 1 of 4 samples (3 unverified)
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 ran 1 of 3 samples (2 unverified)
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders 2 1 5 Dec 2018 ran 2 of 2 samples (0 unverified)
Learning Robust Visual-Semantic Embeddings 0 1 17 Mar 2017 not harvested

Dataset loaders archive 2025-07-28

gas.graviti.com/dataset/graviti/AnimalsWithAttributes2Graviti-AI/datasetstfpytorch

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

Tasks archive 2025-07-28

Zero-Shot LearningFew-Shot Image ClassificationGeneralized Few-Shot LearningGeneralized Zero-Shot LearningConcept-based Classification

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

Images

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