Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention
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 self-calibration loss | DAZLE · CUB proposed split | accuracy: 62.3 -> 65.9 | Helped |
| add self-calibration loss | DAZLE · CUB | unseen accuracy: 42.0 -> 56.7 | Helped |
| add self-calibration loss | DAZLE · SUN | unseen accuracy: 21.7 -> 52.3 | Helped |
| add self-calibration loss | DAZLE · AWA2 | unseen accuracy: 25.7 -> 60.3 | Helped |
| add dense attribute-based attention (ablation) | DAZLE with Lce on DeepFashion · DeepFashion | H: 8.7 -> 10.8 | Helped |
| add dense attribute-based attention (ablation) | DAZLE with Lce + Lcal on DeepFashion · DeepFashion | H: 24.8 -> 26.2 | Helped |
| add attention over attributes (ablation) | DAZLE with Lce + Lcal on DeepFashion · DeepFashion | H: 26.2 -> 27.5 | Helped |
| refine attribute semantic vectors during training rather than fixing them (ablation) | DAZLE with Lce + Lcal on DeepFashion · DeepFashion | H: 25.6 -> 27.5 | Helped |
| add self-calibration loss | DAZLE on SUN · SUN | H: 25.8 -> 33.2 | Hurt |
| use DAZLE with self-calibration rather than CADA-VAE | generalized zero-shot learning · SUN | H: 40.6 -> 33.2 | Hurt |
Closest papers by meaning
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 2025 · similarity 0.91)
- Attribute Prototype Network for Zero-Shot Learning (NeurIPS 2020 · similarity 0.91)
- Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition (NeurIPS 2020 · similarity 0.90)
- Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning (CVPR 2016 · similarity 0.89)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.88)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 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.