Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Domain-Aware Visual Bias Eliminating for Generalized 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 |
|---|---|---|---|
| Add a semantic-free representation to BaseS2V (ablation) | BaseS2V · CUB | H: 43.0 to 49.1 | Helped |
| Add a semantic-free representation to BaseS2V (ablation) | BaseS2V · CUB | H_R: 60.6% to 66.6% | Helped |
| Add cross-attentive second-order embedding (ablation) | BaseS2V with semantic-free representation · CUB | H: 49.1 to 53.2 | Helped |
| Add adaptive margin Softmax to CSE (ablation) | CSE · CUB | H: 53.2 to 55.0 | Helped |
| Add bilinear pooling (ablation) | Base semantic-free representation · CUB | H: 49.1 to 50.8 | Helped |
| Add spatial and channel attention to bilinear pooling (ablation) | Bilinear pooling · CUB | H: 50.8% to 52.4% | Helped |
| Use cross-attentive spatial and channel attention (ablation) | Bilinear pooling with spatial and channel attention · CUB | H: 52.4 to 53.2 | Helped |
| Replace standard Softmax with fixed-margin Softmax (ablation) | CSE · CUB | H: 53.2 to 52.1 | Hurt |
| Replace fixed or standard margin with adaptive margin Softmax (ablation) | CSE · CUB | H: 52.1 to 55.0; 53.2 to 55.0 | Helped |
| Use DVBE instead of ZS3Net | Zero-shot semantic segmentation · Pascal VOC | hIoU: 37.9 to 48.9 | Helped |
Closest papers by meaning
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.88)
- Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning (CVPR 2025 · similarity 0.87)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.87)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.87)
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 2025 · similarity 0.87)
- Non-exemplar Domain Incremental Object Detection via Learning Domain Bias (AAAI 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.