Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Semantic Feature Extraction 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 the MI-based loss to reconstruction training (ablation) | SE-GZSL · AwA1 | acc_h: 58.3 -> 65.4 | Helped |
| Add the MI-based loss to reconstruction training (ablation) | SE-GZSL · AwA2 | acc_h: 61.6 -> 65.5 | Helped |
| Add the MI-based loss to reconstruction training (ablation) | SE-GZSL · CUB | acc_h: 49.9 -> 55.1 | Helped |
| Add the MI-based loss to reconstruction training (ablation) | SE-GZSL · SUN | acc_h: 39.4 -> 41.3 | Helped |
| Add the similarity-based loss to reconstruction and MI training (ablation) | SE-GZSL · AwA1 | acc_h: 65.4 -> 68.1 | Helped |
| Add the similarity-based loss to reconstruction and MI training (ablation) | SE-GZSL · AwA2 | acc_h: 65.5 -> 68.8 | Helped |
| Add the similarity-based loss to reconstruction and MI training (ablation) | SE-GZSL · CUB | acc_h: 55.1 -> 56.4 | Helped |
| Add the similarity-based loss to reconstruction and MI training (ablation) | SE-GZSL · SUN | acc_h: 41.3 -> 43.1 | Helped |
| Add a residual encoder to separate attribute-irrelevant information from the semantic representation (ablation) | SE-GZSL · AwA1 | acc_h: 66.7 -> 68.1 | Helped |
| Add a residual encoder to separate attribute-irrelevant information from the semantic representation (ablation) | SE-GZSL · AwA2 | acc_h: 67.5 -> 68.8 | Helped |
| Add a residual encoder to separate attribute-irrelevant information from the semantic representation (ablation) | SE-GZSL · CUB | acc_h: 55.1 -> 56.4 | Helped |
| Add a residual encoder to separate attribute-irrelevant information from the semantic representation (ablation) | SE-GZSL · SUN | acc_h: 42.1 -> 43.1 | Helped |
Closest papers by meaning
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.92)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.90)
- A Variational Autoencoder with Deep Embedding Model for Generalized Zero-Shot Learning (AAAI 2020 · similarity 0.90)
- Generalized Zero-Shot Recognition Based on Visually Semantic Embedding (CVPR 2019 · similarity 0.90)
- Discriminative Learning of Latent Features for Zero-Shot Recognition (CVPR 2018 · similarity 0.90)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (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.