Research map / Vision-language and multimodal / CLIP and zero-shot
Learning a Deep Embedding Model for 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 |
|---|---|---|---|
| Use the visual feature space rather than the semantic space as the embedding space (ablation) | Deep embedding model · AwA | accuracy: 60.6 -> 86.7 | Helped |
| Use the visual feature space rather than the semantic space as the embedding space (ablation) | Deep embedding model · AwA | N1 skewness: 0.4162 -> -0.4834 | Helped |
| Use the visual feature space rather than the semantic space as the embedding space (ablation) | Deep embedding model · CUB | N1 skewness: 8.2697 -> 2.2594 | Helped |
| Fuse attributes and word vectors | Ours · AwA | accuracy: 86.7 -> 88.1 | Helped |
| Fuse attributes and sentence descriptions | Ours · CUB | accuracy: 58.3 -> 59.0 | Helped |
| Replace least square loss with hinge loss (ablation) | Deep embedding model with visual feature space · AwA | accuracy: 86.7 -> 72.8 | Hurt |
| Replace least square loss with hinge loss (ablation) | Deep embedding model with semantic space · AwA | accuracy: 60.6 -> 57.7 | Hurt |
| Replace the neural embedding model with linear regression from semantic space to visual features (ablation) | Zero-shot embedding model · AwA | accuracy: 74.8 vs. 86.7 | Hurt |
| Replace the neural embedding model with linear regression from semantic space to visual features (ablation) | Zero-shot embedding model · CUB | accuracy: 45.7 vs. 58.3 | Hurt |
Closest papers by meaning
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.91)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.91)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.90)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.89)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.89)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · 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.