Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Generalized Zero-Shot Learning via Synthesized Examples
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 discriminator/regressor feedback to the generator (ablation) | SE-ZSL · SUN, standard split | accuracy: 62.0 -> 64.5 | Helped |
| add discriminator/regressor feedback to the generator (ablation) | SE-ZSL · SUN, proposed split | accuracy: 61.2 -> 63.4 | Helped |
| add discriminator/regressor feedback to the generator (ablation) | SE-ZSL · CUB, standard split | accuracy: 59.8 -> 60.3 | Helped |
| add discriminator/regressor feedback to the generator (ablation) | SE-ZSL · CUB, proposed split | accuracy: 54.1 -> 59.6 | Helped |
| add discriminator/regressor feedback to the generator (ablation) | SE-ZSL · AWA1, standard split | accuracy: 78.4 -> 83.8 | Helped |
| add discriminator/regressor feedback to the generator (ablation) | SE-ZSL · AWA1, proposed split | accuracy: 68.2 -> 69.5 | Helped |
| add discriminator/regressor feedback to the generator (ablation) | SE-ZSL · AWA2, standard split | accuracy: 79.3 -> 80.8 | Helped |
| add discriminator/regressor feedback to the generator (ablation) | SE-ZSL · AWA2, proposed split | accuracy: 66.3 -> 69.2 | Helped |
| train the final classifier using synthesized labeled examples from unseen classes as well as seen classes | SE-GZSL · SUN, CUB, AWA1, and AWA2 | harmonic mean | Helped |
| increase the number of generated examples per class | SE-ZSL classifiers · AWA2 | classification accuracy | Helped |
Closest papers by meaning
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.90)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.89)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (AAAI 2024 · similarity 0.89)
- A Generalization Theory for Zero-Shot Prediction (ICML 2025 · similarity 0.88)
- Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations (NeurIPS 2024 · similarity 0.88)
- Data-Free Generalized Zero-Shot Learning (AAAI 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.