Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Transferable Contrastive Network for Generalized Zero-Shot Learning
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 the knowledge transfer loss L_T (ablation) | TCN · APY (GZSL) | harmonic mean H (%): 10.28 -> 35.05 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · AWA1 (GZSL) | harmonic mean H (%): 16.14 -> 60.03 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · AWA2 (GZSL) | harmonic mean H (%): 15.91 -> 63.43 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · CUB (GZSL) | harmonic mean H (%): 37.84 -> 52.30 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · SUN (GZSL) | harmonic mean H (%): 27.99 -> 33.96 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · APY (ZSL) | top-1 accuracy (%): 37.52 -> 38.93 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · AWA1 (ZSL) | top-1 accuracy (%): 70.15 -> 70.34 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · AWA2 (ZSL) | top-1 accuracy (%): 68.48 -> 71.18 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · CUB (ZSL) | top-1 accuracy (%): 56.62 -> 59.54 | Improved |
| add the knowledge transfer loss L_T (ablation) | TCN · SUN (ZSL) | top-1 accuracy (%): 61.04 -> 61.53 | Improved |
| vary the transfer weight alpha over 0.001, 0.01, 0.1, 1 (ablation) | TCN · CUB | ZSL accuracy and GZSL H: best at alpha = 0.01; tr drops as alpha increases | Mixed |
Closest papers by meaning
- Semantic Contrastive Embedding for Generalized Zero-Shot Learning (IJCV 2022 · similarity 0.90)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.90)
- Semantics Disentangling for Generalized Zero-Shot Learning (ICCV 2021 · similarity 0.90)
- Contrastive Embedding for Generalized Zero-Shot Learning (CVPR 2021 · similarity 0.90)
- Semantics-Guided Contrastive Network for Zero-Shot Object Detection (TPAMI 2022 · similarity 0.89)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · 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.
