AI Paper Atlas

Research map / Benchmarks / AwA

AwA leaderboard

27 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on AwA. Best accuracy: 91.05 (UVF, AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

AwA · accuracy

27 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
191.05UVFUncertainty-Guided View-Strength-Aware Feature Utilization for Multi-View Classification
AAAI 2026 · Table 1
Recognition and long-tail
288.1Ours (attributes + word vectors)
Inception-V2
Learning a Deep Embedding Model for Zero-Shot Learning
CVPR 2017 · Table 1
CLIP and zero-shot
385.34MSplit LBI (β)MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
ICML 2018 · Zero-shot results table
Zero-/few-shot and meta-learning
485.24LLAEFrom Zero-Shot Learning to Cold-Start Recommendation
AAAI 2019 · Table: Accuracy (%) of zero-sh
Zero-/few-shot and meta-learning
584.7SAE (W)Semantic Autoencoder for Zero-Shot Learning
CVPR 2017 · Table (comparative ZSL)
Zero-/few-shot and meta-learning
683.5MFMR-joint
VGG
Matrix Tri-Factorization With Manifold Regularizations for Zero-Shot Learning
CVPR 2017 · Table 2
Zero-/few-shot and meta-learning
782.8LESD (VGG)
VGG-VeryDeep-19
Low-Rank Embedded Ensemble Semantic Dictionary for Zero-Shot Learning
CVPR 2017 · Table 2
Zero-/few-shot and meta-learning
881.3Our approach (Affinity Propagation)Zero Shot Learning via Multi-Scale Manifold Regularization
CVPR 2017 · Table 2
Graph self-supervised learning
979.12Joint Latent Similarity EmbeddingZero-Shot Learning via Joint Latent Similarity Embedding
CVPR 2016 · Zero-shot recognition comparis
Zero-/few-shot and meta-learning
1078.47SMSTransductive Zero-Shot Recognition via Shared Model Space Learning
AAAI 2016 · Table 3
Zero-/few-shot and meta-learning
17 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.