Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Region Graph Embedding Network for Zero-Shot Learning
Guo-Sen Xie, Li Liu, Fan Zhu, Fang Zhao, Zheng Zhang, Yazhou Yao, Jie Qin, Ling Shao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 parts relation reasoning (PRR) branch (ablation) | RGEN · CUB ZSL | MCA (%): 75.0 -> 76.1 | Improved |
| add parts relation reasoning (PRR) branch (ablation) | RGEN · AWA2 ZSL | MCA (%): 72.5 -> 73.6 | Improved |
| add parts relation reasoning (PRR) branch (ablation) | RGEN · SUN ZSL | MCA (%): 63.4 -> 63.8 | Improved |
| add parts relation reasoning (PRR) branch (ablation) | RGEN · APY ZSL | MCA (%): 43.9 -> 44.4 | Improved |
| add parts relation reasoning (PRR) branch (ablation) | RGEN · AWA2 GZSL | H: 69.7 -> 71.5 | Improved |
| add parts relation reasoning (PRR) branch (ablation) | RGEN · CUB GZSL | H: 64.7 -> 66.1 | Improved |
| use two-layer GCN instead of one-layer GCN (ablation) | RGEN PRR branch · CUB ZSL | MCA (%): 75.2 -> 76.1 | Improved |
| use two-layer GCN instead of three-layer GCN (ablation) | RGEN PRR branch · CUB ZSL | MCA (%): 75.1 -> 76.1 | Improved |
| use two-layer GCN instead of one-layer GCN (ablation) | RGEN PRR branch · CUB GZSL | H: 65.4 -> 66.1 | Improved |
| add balance loss in GZSL training (lambda2 > 0) (ablation) | RGEN · CUB and AWA2 GZSL | H/ts | Improved |
| use small eta2 weight for PRR branch at fusion, (eta1, eta2) = (0.9, 0.1) (ablation) | RGEN · CUB and AWA2 ZSL | MCA (%) | Improved |
| vary number of parts K from 1 to 15 (ablation) | RGEN · CUB and AWA2 | MCA and H | No clear effect |
Closest papers by meaning
- Attentive Region Embedding Network for Zero-Shot Learning (CVPR 2019 · similarity 0.92)
- Learning a Deep Embedding Model for Zero-Shot Learning (CVPR 2017 · similarity 0.89)
- Discriminative Learning of Latent Features for Zero-Shot Recognition (CVPR 2018 · similarity 0.89)
- Semantic-guided Reinforced Region Embedding for Generalized Zero-Shot Learning (AAAI 2021 · similarity 0.89)
- Explanatory Object Part Aggregation for Zero-Shot Learning (TPAMI 2023 · similarity 0.89)
- LinkNet: Relational Embedding for Scene Graph (NeurIPS 2018 · 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.
