Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Attentive Region Embedding Network for Zero-Shot 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 |
|---|---|---|---|
| embed attentive local regions instead of relying only on global image features (ablation) | AREN · CUB PS | ACA: 62.7 -> 72.5 | Helped |
| embed attentive local regions instead of relying only on global image features (ablation) | AREN · AWA2 PS | ACA: 60.3 -> 66.9 | Helped |
| add attention-guided compressed second-order features (ablation) | ACSE · CUB PS | ACA: 62.7 -> 71.5 | Helped |
| add attention-guided compressed second-order features (ablation) | ACSE · AWA2 PS | ACA: 60.3 -> 65.2 | Helped |
| add adaptive thresholding to remove low-attention regions (ablation) | ARE · CUB and AWA2, ZSL | ACA | Helped |
| use attention in second-order feature construction (ablation) | ACSE · CUB and AWA2, ZSL | ACA | Helped |
| reduce the compressed channel count (ablation) | ACSE · CUB and AWA2, ZSL | ACA | Helped |
| train ARE and ACSE jointly rather than separately (ablation) | AREN · CUB, AWA2, and APY, ZSL | ACA: 70.7 vs 70.2; 86.7 vs 86.3; 44.1 vs 44.0 | Hurt |
| train ARE and ACSE jointly rather than separately (ablation) | AREN · CUB PS | H: 52.1 vs 51.2; 52.1 vs 48.4 | Mixed |
| add calibrated stacking to reduce seen-class prediction scores (ablation) | AREN · CUB PS | H: 52.1 -> 66.0 | Helped |
| add calibrated stacking to reduce seen-class prediction scores (ablation) | AREN · AWA2 PS | H: 26.7 -> 64.7 | Helped |
Closest papers by meaning
- Discriminative Learning of Latent Features for Zero-Shot Recognition (CVPR 2018 · similarity 0.92)
- Learning a Deep Embedding Model for Zero-Shot Learning (CVPR 2017 · similarity 0.91)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.89)
- 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 0.89)
- ZeroMamba: Exploring Visual State Space Model 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.