Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition
Huajie Jiang, Ruiping Wang, Shiguang Shan, Xilin Chen
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 alignment of visual and semantic prototypes (ablation) | CDL · ZSL on four datasets (aPY, AwA, CUB, SUNA) | accuracy | Improved |
| add the prototype learning term instead of fixing prototypes at class means (ablation) | CDL · ZSL on four datasets | accuracy | Improved |
| add the unseen-class domain adaptation term (ablation) | CDL · ZSL on four datasets | accuracy | Improved |
| combine visual and aligned space similarities instead of using the semantic space alone (ablation) | CDL · aPY, CUB, SUNA | accuracy | Improved |
| combine visual space with other spaces (ablation) | CDL · AwA | accuracy | Hurt |
| recognize in the visual space instead of the semantic space (ablation) | CDL · ZSL on four datasets | accuracy | Improved |
| use CDL instead of ALE for zero-shot recognition | ALE · aPY | accuracy (%): 39.7 -> 43.0 | Improved |
| use CDL instead of SJE for zero-shot recognition | SJE · AwA | accuracy (%): 65.6 -> 69.9 | Improved |
| use CDL instead of ALE for zero-shot recognition | ALE · SUNA | accuracy (%): 58.1 -> 63.6 | Improved |
| use CDL instead of SYNC on fine-grained CUB | SYNC · CUB | accuracy (%): 55.6 -> 54.5 | Hurt |
| use CDL instead of ALE in generalized ZSL | ALE · AwA (generalized ZSL) | harmonic mean H (%): 27.5 -> 40.6 | Improved |
| use CDL instead of ALE in generalized ZSL | ALE · aPY (generalized ZSL) | harmonic mean H (%): 8.7 -> 28.1 | Improved |
Closest papers by meaning
- Zero-Shot Learning on Semantic Class Prototype Graph (TPAMI 2017 · similarity 0.93)
- SimZSL: Zero-Shot Learning Beyond a Pre-defined Semantic Embedding Space (IJCV 2025 · similarity 0.92)
- Domain-Invariant Projection Learning for Zero-Shot Recognition (NeurIPS 2018 · similarity 0.92)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.90)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.90)
- S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment (AAAI 2024 · similarity 0.90)
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.
