Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Semantics Disentangling for Generalized Zero-Shot Learning
Zhi Chen, Yadan Luo, Ruihong Qiu, Sen Wang, Zi Huang, Jingjing Li, Zheng Zhang
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 the total correlation penalty (TC) (ablation) | SDGZSL with relation network · aPaY (GZSL) | harmonic mean H (%): 40.0 -> 45.7 | Improved |
| add the total correlation penalty (TC) (ablation) | SDGZSL with relation network · AWA (GZSL) | harmonic mean H (%): 58.0 -> 68.8 | Improved |
| add the total correlation penalty (TC) (ablation) | SDGZSL with relation network · CUB (GZSL) | harmonic mean H (%): 31.2 -> 63.0 | Improved |
| add the total correlation penalty (TC) (ablation) | SDGZSL with relation network · FLO (GZSL) | harmonic mean H (%): 53.3 -> 86.6 | Improved |
| add the relation network (RN) (ablation) | SDGZSL with total correlation penalty · aPaY (GZSL) | harmonic mean H (%): 33.1 -> 45.7 | Improved |
| add the relation network (RN) (ablation) | SDGZSL with total correlation penalty · AWA (GZSL) | harmonic mean H (%): 55.5 -> 68.8 | Improved |
| add the relation network (RN) (ablation) | SDGZSL with total correlation penalty · CUB (GZSL) | harmonic mean H (%): 25.0 -> 63.0 | Improved |
| add the relation network (RN) (ablation) | SDGZSL with total correlation penalty · FLO (GZSL) | harmonic mean H (%): 50.7 -> 86.6 | Improved |
| add disentangling modules (RN and TC) to the cVAE generator | cVAE · aPaY (GZSL) | harmonic mean H (%): 39.0 -> 45.7 | Improved |
| add disentangling modules (RN and TC) to the cVAE generator | cVAE · AWA (GZSL) | harmonic mean H (%): 62.2 -> 68.8 | Improved |
| add disentangling modules (RN and TC) to the cVAE generator | cVAE · CUB (GZSL) | harmonic mean H (%): 52.7 -> 63.0 | Improved |
| add disentangling modules (RN and TC) to the cVAE generator | cVAE · FLO (GZSL) | harmonic mean H (%): 71.9 -> 86.6 | Improved |
Closest papers by meaning
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.94)
- Generalized Zero-Shot Learning via Disentangled Representation (AAAI 2021 · similarity 0.93)
- Distinguishing Unseen From Seen for Generalized Zero-Shot Learning (CVPR 2022 · similarity 0.93)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (AAAI 2024 · similarity 0.91)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.91)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.91)
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.
