Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-shot Learning via Simultaneous Generating and Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add simultaneous generating-and-learning on unseen classes (ablation) | mmVAE · AwA2 GZSL | harmonic mean H: 26.9 -> 65.3 | Helped |
| add simultaneous generating-and-learning on unseen classes (ablation) | mmVAE · AwA1 GZSL | harmonic mean H: 54.2 -> 61.5 | Helped |
| add simultaneous generating-and-learning on unseen classes (ablation) | mmVAE · CUB GZSL | harmonic mean H: 39.3 -> 47.0 | Helped |
| add simultaneous generating-and-learning on unseen classes (ablation) | mmVAE · SUN GZSL | harmonic mean H: 21.4 -> 34.9 | Helped |
| add simultaneous generating-and-learning on unseen classes (ablation) | mmVAE · AwA 10-way 0-shot | accuracy: 74.2 -> 84.1 | Helped |
| add simultaneous generating-and-learning on unseen classes (ablation) | mmVAE · CUB 50-way 0-shot | accuracy: 58.4 -> 62.5 | Helped |
| add simultaneous generating-and-learning on unseen classes (ablation) | mmVAE · AwA2 GZSL | seen accuracy s: 92.6 -> 86.3 | Hurt |
| activate dropout when sampling unseen datapoints (ablation) | SGAL · AwA2 GZSL | harmonic mean H: 65.3 -> 65.6 | Helped |
| activate dropout when sampling unseen datapoints (ablation) | SGAL · SUN GZSL | unseen accuracy u: 35.5 -> 42.9 | Helped |
| activate dropout when sampling unseen datapoints (ablation) | SGAL · CUB GZSL | harmonic mean H: 47.0 -> 45.9 | Hurt |
| activate dropout when sampling unseen datapoints (ablation) | SGAL · AwA1 GZSL | harmonic mean H: 61.5 -> 62.2 | Helped |
Closest papers by meaning
- Zero-Shot Learning via Class-Conditioned Deep Generative Models (AAAI 2018 · similarity 0.95)
- Adaptive and Generative Zero-Shot Learning (ICLR 2021 · similarity 0.91)
- Generalized Zero-Shot Learning via Synthesized Examples (CVPR 2018 · similarity 0.91)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.89)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.88)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.