AI Paper Atlas

Research map / Benchmarks / aPY

aPY leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on aPY. Best H: 56.2 (Ours(Π), CVPR 2019).

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.

aPY · H

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

#H ↑MethodPaperTopic
156.2Ours(Π)Generalized Zero-Shot Recognition Based on Visually Semantic Embedding
CVPR 2019 · Table 1
Zero-/few-shot and meta-learning
250.5DGZ*
fine-tuned features
Deconstructed Generation-Based Zero-Shot Model
AAAI 2023 · Table 1
Zero-/few-shot and meta-learning
348.4DPPN
ResNet-101
Dual Progressive Prototype Network for Generalized Zero-Shot Learning
NeurIPS 2021 · Table: Results of GZSL
Zero-/few-shot and meta-learning
447.6IPN
ResNet-101
Isometric Propagation Network for Generalized Zero-shot Learning
ICLR 2021 · Table: Performance of existing
Zero-/few-shot and meta-learning
547.6DASCNDual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
NeurIPS 2019 · Table 2
Zero-/few-shot and meta-learning
647.4f-CLSWGAN+SDFA²
f-CLSWGAN
Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
AAAI 2022 · Table 1
Zero-/few-shot and meta-learning
746.7DCENTask-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
AAAI 2021 · GZSL results table
Zero-/few-shot and meta-learning
846.4SR2E
ResNet101
Semantic-guided Reinforced Region Embedding for Generalized Zero-Shot Learning
AAAI 2021 · Table 1
Open-set and few-shot detection
945.7ICCE
ResNet101
En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
CVPR 2022 · Table 1
Zero-/few-shot and meta-learning
1045.2DVBE*
ResNet-101
Domain-Aware Visual Bias Eliminating for Generalized Zero-Shot Learning
CVPR 2020 · Table: Results of GZSL on four
Zero-/few-shot and meta-learning
5 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.