Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
Shiming Chen, Guosen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, 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 structure adaptation (SAD) constraints (ablation) | HSVA · AWA1 GZSL | harmonic mean H: 62.3 -> 66.8 | Improved |
| add structure adaptation (SAD) constraints (ablation) | HSVA · CUB GZSL | harmonic mean H: 53.2 -> 55.3 | Improved |
| add structure adaptation (SAD) constraints (ablation) | HSVA · SUN GZSL | harmonic mean H: 42.6 -> 43.3 | Improved |
| add distribution adaptation (Wasserstein + iCORAL) constraints (ablation) | HSVA · AWA1 GZSL | harmonic mean H: 43.4 -> 66.8 | Improved |
| add distribution adaptation (Wasserstein + iCORAL) constraints (ablation) | HSVA · CUB GZSL | harmonic mean H: 47.9 -> 55.3 | Improved |
| add distribution adaptation (Wasserstein + iCORAL) constraints (ablation) | HSVA · SUN GZSL | harmonic mean H: 38.6 -> 43.3 | Improved |
| add inverse CORAL loss (ablation) | HSVA · AWA1 GZSL | harmonic mean H: 62.4 -> 66.8 | Improved |
| add inverse CORAL loss (ablation) | HSVA · AWA2 GZSL | harmonic mean H: 63.3 -> 66.3 | Improved |
| add inverse CORAL loss (ablation) | HSVA · CUB GZSL | harmonic mean H: 53.9 -> 55.3 | Improved |
| add inverse CORAL loss (ablation) | HSVA · SUN GZSL | harmonic mean H: 41.8 -> 43.3 | Improved |
| add structure adaptation (SAD) constraints (ablation) | HSVA · AWA2 GZSL | harmonic mean H: 63.5 -> 66.3 | Improved |
Later papers that compared with this method
3 later accepted papers report HSVA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Mutually Causal Semantic Distillation Network for Zero-Shot Learning (IJCV 2026 · better on 0 of 1 shared result)
- Evolving Semantic Prototype Improves Generative Zero-Shot Learning (ICML 2023 · better on 1 of 1 shared result)
- MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning (CVPR 2022 · better on 0 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 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 0.89)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.89)
- 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)
- Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label 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.
