Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Progressive Semantic-Visual Mutual Adaption for Generalized 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 |
|---|---|---|---|
| add semantic-related instance attention using sharing attributes (ablation) | PSVMA baseline · CUB | H: 63.8 -> 67.1 | Helped |
| add semantic-related instance attention using sharing attributes (ablation) | PSVMA baseline · SUN | H: 36.0 -> 41.3 | Helped |
| add semantic-related instance attention using sharing attributes (ablation) | PSVMA baseline · AwA2 | H: 67.8 -> 69.3 | Helped |
| add patch mixing and activation (ablation) | PSVMA with SRIA · CUB | H: 67.1 -> 70.0 | Helped |
| add patch mixing and activation (ablation) | PSVMA with SRIA · SUN | H: 41.3 -> 49.4 | Helped |
| add patch mixing and activation (ablation) | PSVMA with SRIA · AwA2 | H: 69.3 -> 70.6 | Helped |
| add instance-aware semantic attention (ablation) | PSVMA with SRIA and PMA · CUB | H: 70.0 -> 71.3 | Helped |
| add instance-aware semantic attention (ablation) | PSVMA with SRIA and PMA · SUN | H: 49.4 -> 51.2 | Helped |
| add instance-aware semantic attention (ablation) | PSVMA with SRIA and PMA · AwA2 | H: 70.6 -> 74.5 | Helped |
| add attribute communication and activation (ablation) | PSVMA with SRIA, PMA, and IASA · CUB | H: 71.3 -> 73.8 | Helped |
| add attribute communication and activation (ablation) | PSVMA with SRIA, PMA, and IASA · SUN | H: 51.2 -> 52.3 | Helped |
| add attribute communication and activation (ablation) | PSVMA with SRIA, PMA, and IASA · AwA2 | H: 74.5 -> 75.4 | Helped |
Closest papers by meaning
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.92)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.90)
- Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning (CVPR 2024 · similarity 0.90)
- Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning (AAAI 2025 · similarity 0.90)
- Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning (CVPR 2025 · similarity 0.89)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 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.