Research map / Detection and segmentation / Open-set and few-shot detection
Semantic-guided Reinforced Region Embedding for Generalized Zero-Shot Learning
Jiannan Ge, Hongtao Xie, Shaobo Min, Yongdong Zhang
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 the difference-based domain detector (ablation) | SE-BS · CUB | H: 55.4 -> 63.5 | Improved |
| add the difference-based domain detector (ablation) | SE-BS · AwA2 | H: 25.7 -> 65.9 | Improved |
| add the difference-based domain detector (ablation) | SE-BS · SUN | H: 24.7 -> 38.9 | Improved |
| add the difference-based domain detector (ablation) | SE-BS · aPY | H: 16.7 -> 44.4 | Improved |
| add semantic-guided reinforced region search (ablation) | SE-DD · CUB | H: 63.5 -> 65.8 | Improved |
| add semantic-guided reinforced region search (ablation) | SE-DD · AwA2 | H: 65.9 -> 67.5 | Improved |
| add semantic-guided reinforced region search (ablation) | SE-DD · SUN | H: 38.9 -> 39.7 | Improved |
| add semantic-guided reinforced region search (ablation) | SE-DD · aPY | H: 44.4 -> 46.4 | Improved |
| vary search scale factor α among 4/5, 6/7, and 9/10 (ablation) | SR2E · CUB | H: 64.7; 65.8; 64.9 | Mixed |
| vary search scale factor α among 4/5, 6/7, and 9/10 (ablation) | SR2E · aPY | H: 44.4; 45.7; 46.4 | Mixed |
| use d=1 rather than d=0 for omitting termination actions (ablation) | SR2E · CUB | H: 64.8 -> 65.8 | Improved |
| use d=2 rather than d=0 for omitting termination actions (ablation) | SR2E · CUB | H: 64.8 -> 65.0 | Improved |
Closest papers by meaning
- Attentive Region Embedding Network for Zero-Shot Learning (CVPR 2019 · similarity 0.91)
- Generalized Zero-Shot Recognition Based on Visually Semantic Embedding (CVPR 2019 · similarity 0.91)
- Semantic-Guided Multi-Attention Localization for Zero-Shot Learning (NeurIPS 2019 · similarity 0.91)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.90)
- TransZero: Attribute-Guided Transformer for Zero-Shot Learning (AAAI 2022 · similarity 0.90)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.89)
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.
