Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
A Variational Autoencoder with Deep Embedding Model for Generalized Zero-Shot 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 deep embedding mapping (semantic to visual space) before the VAE, replacing CADA-VAE's two encoders | CADA-VAE baseline · CUB GZSL | harmonic mean H (%): 52.5 -> 54.3 | Helped |
| add deep embedding mapping before the VAE | CADA-VAE baseline · SUN GZSL | harmonic mean H (%): 39.9 -> 40.9 | Helped |
| add deep embedding mapping before the VAE | CADA-VAE baseline · AWA1 GZSL | harmonic mean H (%): 63.6 -> 66.9 | Helped |
| add deep embedding mapping before the VAE | CADA-VAE baseline · AWA2 GZSL | harmonic mean H (%): 64.1 -> 67.4 | Helped |
| combine DE and VAE (DE-VAE) versus DE alone or VAE alone (ablation) | DE-VAE · four GZSL benchmarks | harmonic mean H | Helped |
| add VAE-generated unseen latent features versus deep embedding alone (ablation) | deep embedding network · four GZSL benchmarks | harmonic mean H | Helped |
| vary deep embedding loss weight lambda from 0.01 to 100 (ablation) | DE-VAE · CUB GZSL | harmonic mean H: 51.99 (0.01), 54.23 (1), 52.60 (100) | Mixed |
Closest papers by meaning
- Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders (CVPR 2019 · similarity 0.92)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.91)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.90)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.90)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (AAAI 2024 · similarity 0.89)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.88)
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.