Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Low-Rank Embedded Ensemble Semantic Dictionary 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 LESD with a VGG-VeryDeep-19 feature representation | zero-shot classification · aP&aY | accuracy: 53.2 -> 55.2 | Helped |
| use LESD with a VGG-VeryDeep-19 feature representation | zero-shot classification · AwA | accuracy: 80.5 -> 82.8 | Helped |
| use LESD with a VGG-VeryDeep-19 feature representation | zero-shot classification · CUB | accuracy: 43.7 -> 45.2 | Helped |
| use LESD with a VGG-VeryDeep-19 feature representation | zero-shot classification · SUN | accuracy: 84.4 -> 86.0 | Helped |
| use LESD with AlexNet features | zero-shot classification · aP&aY | accuracy: 46.1 -> 48.9 | Helped |
| use LESD with AlexNet features | zero-shot classification · AwA | accuracy: 73.2 -> 71.4 | Hurt |
| use LESD with AlexNet features | zero-shot classification · CUB | accuracy: 47.1 -> 43.9 | Hurt |
| use LESD with AlexNet features | zero-shot classification · SUN | accuracy: 75.5 -> 77.1 | Helped |
| use LESD with GoogLeNet features | zero-shot classification · AwA | accuracy: 72.9 -> 76.6 | Helped |
| use LESD with GoogLeNet features | zero-shot classification · CUB | accuracy: 54.5 -> 56.2 | Helped |
| use LESD with GoogLeNet features | zero-shot classification · SUN | accuracy: 90.0 -> 88.3 | Hurt |
| increase the number of seen classes from 50 to 100 or 150 | LESD on CUB with 50 unseen classes · CUB | accuracy: 40.2 -> 51.2; 40.2 -> 55.9 | Helped |
Closest papers by meaning
- Generalized Zero-Shot Recognition Based on Visually Semantic Embedding (CVPR 2019 · similarity 0.89)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.87)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.87)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.87)
- Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning (AAAI 2025 · similarity 0.87)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 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.