Research map / Continual learning / Class-incremental
MetaZSCIL: A Meta-Learning Approach for Generalized Zero-Shot Class Incremental 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 |
|---|---|---|---|
| Use MetaZSCIL instead of Online-CGZSL | CI-GZSL · AWA1 | Final-session harmonic mean accuracy: +5.85% | Helped |
| Use MetaZSCIL instead of Online-CGZSL | CI-GZSL · AWA2 | Final-session harmonic mean accuracy: +9.72% | Helped |
| Use MetaZSCIL instead of Online-CGZSL | CI-GZSL · aPY | Final-session harmonic mean accuracy: +9.01% | Helped |
| Use MetaZSCIL instead of Online-CGZSL | CI-GZSL · SUN | Final-session harmonic mean accuracy: +4.40% | Helped |
| Use MetaZSCIL instead of Online-CGZSL | CI-GZSL · CUB | Final-session harmonic mean accuracy: +7.07% | Helped |
| Add class consistency loss (LCC) (ablation) | Sequential f-CLSWGAN on AWA1 · AWA1 | Mean harmonic accuracy (mH): 54.31 -> 73.78 | Helped |
| Add sample diversity loss (LSD) (ablation) | Sequential f-CLSWGAN on AWA1 · AWA1 | Mean harmonic accuracy (mH): 54.31 -> 74.62 | Helped |
| Add meta-learning optimization to the model with LCC and LSD (ablation) | MetaZSCIL on AWA1 · AWA1 | Mean harmonic accuracy (mH): 74.62 -> 76.07 | Helped |
| Increase the number of sequential tasks in meta-training (ablation) | MetaZSCIL · CUB and SUN | Mean harmonic accuracy (mH) | Mixed |
| Increase the number of replayed samples per unseen class (ablation) | MetaZSCIL · AWA1 and AWA2 | Mean harmonic accuracy (mH) | Helped |
Closest papers by meaning
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.90)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (AAAI 2024 · similarity 0.89)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.89)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.88)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.87)
- Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning (CVPR 2025 · similarity 0.87)
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.