Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-Shot Classification With Discriminative Semantic Representation 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 label propagation instead of direct prototype matching (ablation) | DSRL · AwA | multi-class classification accuracy: 77.38±0.06 -> 87.22±0.27 | Helped |
| Use label propagation instead of direct prototype matching (ablation) | DSRL · CUB | multi-class classification accuracy: 50.26±0.04 -> 57.14±0.07 | Helped |
| Use label propagation instead of direct prototype matching (ablation) | DSRL · SUN | multi-class classification accuracy: 82.00±0.00 -> 85.40±0.22 | Helped |
| Use label propagation instead of direct prototype matching (ablation) | DSRL · aPY | multi-class classification accuracy: 56.29±0.44 -> 51.29±1.42 | Hurt |
| Add latent dictionary components beyond the attribute components (ablation) | DSRL · AwA and CUB | accuracy | Helped |
| Increase the number of additional latent components excessively (ablation) | DSRL · CUB | accuracy | Hurt |
Closest papers by meaning
- Discriminative Learning of Latent Features for Zero-Shot Recognition (CVPR 2018 · similarity 0.90)
- Preserving Semantic Relations for Zero-Shot Learning (CVPR 2018 · similarity 0.89)
- Zero-Shot Learning via Joint Latent Similarity Embedding (CVPR 2016 · similarity 0.89)
- Zero-Shot Kernel Learning (CVPR 2018 · similarity 0.89)
- Label Propagation for Zero-shot Classification with Vision-Language Models (CVPR 2024 · similarity 0.88)
- Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label 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.