Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
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 SDFA² attribute augmentation | f-CLSWGAN · AWA, CUB, aPY, SUN | H: 59.6 -> 65.2; 49.7 -> 54.3; 42.9 -> 47.4; 39.4 -> 42.0 | Helped |
| Add SDFA² attribute augmentation | f-VAEGAN-D2 · AWA, CUB, aPY, SUN | H: 63.7 -> 64.7; 53.5 -> 54.2; 39.2 -> 46.8; 41.8 -> 42.4 | Helped |
| Add SDFA² attribute augmentation | RFF-GZSL · AWA, CUB, aPY, SUN | H: 61.5 -> 65.0; 54.4 -> 54.7; 30.6 -> 38.9; 39.9 -> 40.1 | Helped |
| Add SDFA² attribute augmentation | CE-GZSL · AWA, CUB, aPY, SUN | H: 64.7 -> 66.2; 53.0 -> 54.0; 17.3 -> 34.3; 37.9 -> 38.2 | Helped |
| Add diversity generation loss (ablation) | f-CLSWGAN · AWA1, aPY, SUN, CUB | H: 59.6 -> 64.5; 42.9 -> 47.1; 39.4 -> 40.5; 49.7 -> 54.1 | Helped |
| Add self-supervision loss to diversity generation (ablation) | f-CLSWGAN+L_div-gan · AWA1, aPY, SUN, CUB | H: 64.5 -> 65.2; 47.1 -> 47.4; 40.5 -> 42.0; 54.1 -> 54.3 | Helped |
| Vary the number of attribute groups (ablation) | f-CLSWGAN+SDFA² · AWA1, aPY, SUN, CUB | H | No clear effect |
| Vary the proportion of synthesized diverse features (ablation) | SDFA² · AWA1, aPY, SUN, CUB | H | Mixed |
Closest papers by meaning
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.92)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.92)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.91)
- Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning (CVPR 2024 · similarity 0.90)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (AAAI 2024 · similarity 0.89)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.89)
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.