Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Creativity Inspired Zero-Shot Learning
Mohamed Elhoseiny, Mohamed Elfeki
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 entropy-maximization term on hallucinated text (ablation) | GAZSL+CIZSL · CUB easy split | Seen-Unseen AUC: 33.3 -> 39.2 | Improved |
| add entropy-maximization term on hallucinated text (ablation) | GAZSL+CIZSL · CUB hard split | Seen-Unseen AUC: 10.1 -> 11.9 | Improved |
| add realism (discriminator real) term on hallucinated text (ablation) | GAZSL+CIZSL · CUB easy split | Seen-Unseen AUC: 35.0 -> 39.2 | Improved |
| add realism (discriminator real) term on hallucinated text (ablation) | GAZSL+CIZSL · CUB hard split | Seen-Unseen AUC: 8.2 -> 11.9 | Improved |
| use entropy deviation instead of classifying hallucinated text as a new class (ablation) | GAZSL+CIZSL · CUB hard split | Seen-Unseen AUC: 9.5 -> 11.9 | Improved |
| learn Sharma-Mittal entropy parameters instead of fixed KL (ablation) | GAZSL+CIZSL · CUB hard split | Seen-Unseen AUC: 11.6 -> 11.9 | Improved |
| add CIZSL loss to GAZSL | GAZSL · CUB easy split | Seen-Unseen AUC: 35.4 -> 39.2 | Improved |
| add CIZSL loss to GAZSL | GAZSL · CUB hard split | Seen-Unseen AUC: 8.7 -> 11.9 | Improved |
| add CIZSL loss to FeatGen | FeatGen · CUB easy split | Seen-Unseen AUC: 34.1 -> 37.4 | Improved |
| add CIZSL loss to GAZSL | GAZSL · AwA2 attribute ZSL | Top-1 accuracy: 58.9 -> 67.8 | Improved |
| add CIZSL loss to FeatGen | FeatGen · SUN attribute ZSL | Top-1 accuracy: 60.8 -> 59.4 | Hurt |
| add CIZSL loss to GAZSL | GAZSL · CUB zero-shot retrieval (100%) | mAP: 40.3 -> 46.2 | Improved |
Closest papers by meaning
- Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning (ECCV 2020 · similarity 0.90)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.89)
- Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective (ICCV 2019 · similarity 0.89)
- Adaptive and Generative Zero-Shot Learning (ICLR 2021 · similarity 0.89)
- A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.87)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · 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.
