Research map / Continual learning / Class-incremental
Unseen Classes at a Later Time? No Problem
Check 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 the proposed framework rather than CA +mem | Online-CGZSL · aPY | mH: 46.07 -> 49.11 | Helped |
| use the proposed framework rather than CA +mem | Online-CGZSL · AWA1 | mH: 67.15 -> 73.33 | Helped |
| use the proposed framework rather than CA +mem | Online-CGZSL · AWA2 | mH: 64.90 -> 75.44 | Helped |
| use the proposed framework rather than NM-ZSL | Online-CGZSL · CUB | mH: 54.9 -> 48.03 | Hurt |
| use the proposed framework rather than Tf-GCZSL | Online-CGZSL · SUN | mH: 37.81 -> 43.20 | Helped |
| add generative replay (ablation) | proposed framework · AWA1 Online-CGZSL | mH: 20.24 -> 73.33 | Helped |
| add semantic alignment loss L_sal (ablation) | proposed framework · AWA1 Online-CGZSL | mH: 69.10 -> 73.33 | Helped |
| add nuclear loss (ablation) | proposed framework · AWA1 Online-CGZSL | mH: 69.31 -> 73.33 | Helped |
| add both alignment losses (ablation) | proposed framework · AWA1 Online-CGZSL | mH: 56.38 -> 73.33 | Helped |
| add real and pseudo-visual classification losses (ablation) | proposed framework · AWA1 Online-CGZSL | mH: 45.65 -> 73.33 | Helped |
| add seen-normalized loss L_snl (ablation) | proposed framework · AWA1 Online-CGZSL | mH: 67.74 -> 73.33 | Helped |
| add replay and real/pseudo-visual classification losses (ablation) | proposed framework · AWA1 Online-CGZSL | mH: 4.29 -> 73.33 | Helped |
Closest papers by meaning
- MetaZSCIL: A Meta-Learning Approach for Generalized Zero-Shot Class Incremental Learning (AAAI 2023 · similarity 0.93)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.91)
- Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (AAAI 2024 · similarity 0.90)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.88)
- Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations (NeurIPS 2024 · similarity 0.87)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · 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.