Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Attribute Propagation Network for Graph 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 |
|---|---|---|---|
| use APNet instead of CRNet | ZSL classifiers · SUN (GZSL) | H: 35.3 -> 37.8 | Helped |
| use APNet instead of CRNet | ZSL classifiers · CUB (GZSL) | H: 50.5 -> 51.7 | Helped |
| use APNet instead of CRNet | ZSL classifiers · AWA1 (GZSL) | H: 65.4 -> 67.1 | Helped |
| use APNet instead of CRNet | ZSL classifiers · AWA2 (GZSL) | H: 63.1 -> 66.4 | Helped |
| use APNet instead of CRNet | ZSL classifiers · aPY (GZSL) | H: 44.0 -> 45.5 | Helped |
| use APNet instead of strongest listed baseline | ZSL classifiers · SUN (ZSL) | per-class accuracy: 62.2 -> 62.3 | Helped |
| use APNet instead of strongest listed baseline | ZSL classifiers · CUB (ZSL) | per-class accuracy: 55.6 -> 57.7 | Helped |
| use APNet instead of strongest listed baseline | ZSL classifiers · AWA1 (ZSL) | per-class accuracy: 68.2 -> 68.0 | Hurt |
| use APNet instead of strongest listed baseline | ZSL classifiers · AWA2 (ZSL) | per-class accuracy: 67.4 -> 68.0 | Helped |
| use APNet instead of strongest listed baseline | ZSL classifiers · aPY (ZSL) | per-class accuracy: 44.3 -> 41.3 | Hurt |
| add graph propagation (ablation) | APNet with meta-training on AWA2 · AWA2 (GZSL) | H: 65.4 -> 66.4 | Helped |
| add meta-training (ablation) | APNet without graph propagation on AWA2 · AWA2 (GZSL) | H: 62.5 -> 65.4 | Helped |
Closest papers by meaning
- Isometric Propagation Network for Generalized Zero-shot Learning (ICLR 2021 · similarity 0.93)
- Graph Knows Unknowns: Reformulate Zero-Shot Learning as Sample-Level Graph Recognition (AAAI 2023 · similarity 0.90)
- Zero-Shot Learning With Attribute Selection (AAAI 2018 · similarity 0.90)
- Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis (NeurIPS 2022 · similarity 0.89)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.88)
- Label Propagation for Zero-shot Classification with Vision-Language Models (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.