Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Leveraging the Invariant Side of Generative Zero-Shot Learning
Check 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 soul-sample regularization to conditional WGAN (ablation) | LisGAN · aPaY zero-shot learning | top-1 accuracy | Helped |
| Use multiple soul samples per class instead of a single prototype (ablation) | LisGAN · Zero-shot learning with multi-view visual features | top-1 accuracy | Helped |
| Add the cascade classifier that leverages low-entropy predictions (ablation) | LisGAN · Zero-shot recognition | classification accuracy | Helped |
| Add supervised classification loss (ablation) | LisGAN conditional WGAN · Generated visual features | discriminative quality | Helped |
| Vary the number of soul-sample clusters per class (ablation) | LisGAN · aPaY zero-shot learning | top-1 accuracy | No clear effect |
| Increase the number of synthesized samples per class (ablation) | LisGAN · Zero-shot learning | top-1 accuracy | Helped |
| Set the classification-loss and soul-sample regularization weights relatively small (ablation) | LisGAN · Zero-shot learning | top-1 accuracy | Helped |
| Set the entropy threshold below the median entropy (ablation) | LisGAN cascade classifier · Zero-shot recognition | classification accuracy | Helped |
Closest papers by meaning
- Feature Generating Networks for Zero-Shot Learning (CVPR 2018 · similarity 0.93)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.88)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.88)
- Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning (CVPR 2024 · similarity 0.87)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.87)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (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.