Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Episode-Based Prototype Generating Network for Zero-Shot Learning
Yunlong Yu, Zhong Ji, Jungong Han, Zhongfei Zhang
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 |
|---|---|---|---|
| Train with the episode-based paradigm instead of batch-based PGN training (ablation) | PGN · AwA1, AwA2, CUB, FLO | H: 65.3 -> 71.2; 61.0 -> 64.6; 52.5 -> 56.2; 70.0 -> 76.5 | Improved |
| Use 5 rather than 10 mimetic unseen classes per episode (ablation) | E-PGN · AwA1, AwA2, CUB, FLO | H: 68.0 vs 71.2; 63.3 vs 64.6; 54.4 vs 56.2; 73.2 vs 76.5 | Hurt |
| Use 15 rather than 10 mimetic unseen classes per episode (ablation) | E-PGN · AwA1, AwA2, CUB, FLO | H: 71.1 vs 71.2; 63.1 vs 64.6; 54.3 vs 56.2; 75.2 vs 76.5 | Mixed |
| Add MCE loss (ablation) | E-PGN · AwA1, AwA2, CUB, FLO | H: 66.8 -> 71.2; 56.1 -> 64.6; 48.8 -> 56.2; 74.4 -> 76.5 | Improved |
| Add visual-to-semantic regression loss (ablation) | E-PGN · AwA1, AwA2, CUB, FLO | H: 69.6 -> 71.2; 63.0 -> 64.6; 54.7 -> 56.2; 74.1 -> 76.5 | Improved |
| Add semantic-to-visual regression loss (ablation) | E-PGN · AwA1, AwA2, CUB, FLO | H: 70.4 -> 71.2; 64.3 -> 64.6; 50.4 -> 56.2; 75.2 -> 76.5 | Improved |
| Use MCE rather than traditional cross-entropy (ablation) | E-PGN · AwA1, AwA2, CUB, FLO | classification performance | Improved |
| Use Euclidean rather than cosine distance (ablation) | E-PGN · four ZSL datasets | classification performance | Improved |
| Use E-PGN rather than the strongest listed baseline | Zero-shot classification · AwA1, AwA2, CUB, FLO | T: 71.1 -> 74.4; 70.4 -> 73.4; 71.1 -> 72.4; 83.9 -> 85.7 | Improved |
| Use E-PGN rather than the strongest listed baseline | Generalized zero-shot classification · AwA1, AwA2, CUB, FLO | H: 64.1 -> 71.2; 63.9 -> 64.6; 54.3 -> 56.2; 68.3 -> 76.5 | Improved |
Closest papers by meaning
- Prototype Matters: Domain-Wise Prototype Induction for Zero-Shot Recognition (TPAMI 2026 · similarity 0.91)
- Zero-Shot Learning via Class-Conditioned Deep Generative Models (AAAI 2018 · similarity 0.90)
- Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective (ICCV 2019 · similarity 0.90)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.89)
- Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning (CVPR 2024 · similarity 0.89)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · 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.
