AI Paper Atlas

Research map / Benchmarks / AWA1 GZSL

AWA1 GZSL leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on AWA1 GZSL. Best harmonic mean H: 72.6 (Ours (gamma=0.95), ECCV 2020).

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.

AWA1 GZSL · harmonic mean H

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

#harmonic mean H ↑MethodPaperTopic
172.6Ours (gamma=0.95)
f-CLSWGAN unseen expert
A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning
ECCV 2020 · Table 3
Zero-/few-shot and meta-learning
269.1CE-GZSL
ResNet-101 features
Semantic Contrastive Embedding for Generalized Zero-Shot Learning
IJCV 2022 · Table 1
Zero-/few-shot and meta-learning
366.9DE-VAE
ResNet101 features
A Variational Autoencoder with Deep Embedding Model for Generalized Zero-Shot Learning
AAAI 2020 · Table 2
Zero-/few-shot and meta-learning
466.8HSVA
ResNet-101 features
HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
NeurIPS 2021 · Table 2
Zero-/few-shot and meta-learning
566FREE
ResNet-101 features
FREE: Feature Refinement for Generalized Zero-Shot Learning
ICCV 2021 · Table 1
Zero-/few-shot and meta-learning
665.4CRnet (Ours)
ResNet-101 features
Co-Representation Network for Generalized Zero-Shot Learning
ICML 2019 · Table 1
Zero-/few-shot and meta-learning
763.5ZSML SoftmaxMeta-Learning for Generalized Zero-Shot Learning
AAAI 2020 · Table 1
Zero-/few-shot and meta-learning
863.2TAFE-NetTAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
CVPR 2019 · Table: ZSL and GZSL results
Zero-/few-shot and meta-learning
962.2SGAL-dropout
ResNet101
Zero-shot Learning via Simultaneous Generating and Learning
NeurIPS 2019 · Table 2
Zero-/few-shot and meta-learning
1061.8OursLearning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning
ICCV 2019 · Table 2
Zero-/few-shot and meta-learning

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