Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Dual Progressive Prototype Network 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 PCC to Base-V2S (ablation) | Base-V2S · CUB | H: 63.2 -> 64.3 | Helped |
| Add PCC to Base-V2S (ablation) | Base-V2S · aPY | H: 35.5 -> 40.2 | Helped |
| Add PAL to Base-V2S (ablation) | Base-V2S · CUB | H: 63.2 -> 68.1 | Helped |
| Add PAL to Base-V2S (ablation) | Base-V2S · aPY | H: 35.5 -> 41.8 | Helped |
| Combine PCC and PAL, and increase K from 1 to 3 (ablation) | DPPN · CUB | H: 70.3 -> 73.5 | Helped |
| Combine PCC and PAL, and increase K from 1 to 3 (ablation) | DPPN · aPY | H: 44.4 -> 48.4 | Helped |
| Increase prototype update iterations K from 1 to 3 (ablation) | DPPN · CUB, AWA2, aPY, SUN | H | Helped |
| Set K above 3 (ablation) | DPPN · GZSL benchmarks | H | Hurt |
| Remove prototype refinement function f_ar (ablation) | DPPN · CUB | H: 73.5 -> 72.4 | Hurt |
| Remove prototype refinement function f_ar (ablation) | DPPN · aPY | H: 48.4 -> 45.5 | Hurt |
| Replace concatenation with sum pooling (ablation) | DPPN · CUB | H: 73.5 -> 68.7 | Hurt |
| Replace concatenation with sum pooling (ablation) | DPPN · aPY | H: 48.4 -> 45.2 | Hurt |
Closest papers by meaning
- Attribute Prototype Network for Zero-Shot Learning (NeurIPS 2020 · similarity 0.91)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.89)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.88)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.88)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.88)
- Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning (AAAI 2025 · 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.