Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Evolving Semantic Prototype Improves Generative Zero-Shot Learning
Shiming Chen, Wenjin Hou, Ziming Hong, Xiaohan Ding, Yibing Song, Xinge You, Tongliang Liu, Kun 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 DSP to f-VAEGAN | f-VAEGAN · CUB (GZSL) | H: 52.9 -> 67.4 | Improved |
| Add DSP to f-VAEGAN | f-VAEGAN · SUN (GZSL) | H: 41.3 -> 48.1 | Improved |
| Add DSP to f-VAEGAN | f-VAEGAN · AWA2 (GZSL) | H: 63.5 -> 74.2 | Improved |
| Add DSP to CLSWGAN, TF-VAEGAN, or FREE | Generative ZSL models · CUB, SUN, and AWA2 (GZSL) | H: 49.7 -> 56.9; 39.4 -> 45.5; 59.6 -> 70.7; 57.5 -> 62.8; 42.1 -> 51.7; 66.3 -> 74.8; 57.7 -> 64.6; 41.7 -> 51.0; 67.1 -> | Improved |
| Add semantic cycle consistency loss (ablation) | DSP with f-VAEGAN · CUB and SUN (GZSL) | H: 61.9 -> 67.4; 46.0 -> 48.1 | Improved |
| Add semantic reconstruction loss (ablation) | DSP with f-VAEGAN · CUB and SUN (GZSL) | H: 65.5 -> 67.4; 45.4 -> 48.1 | Improved |
| Add visual-to-semantic loss supervising prototype evolution (ablation) | DSP with f-VAEGAN · CUB and SUN (GZSL) | H: 59.9 -> 67.4; 42.7 -> 48.1 | Improved |
| Use smooth moving-average prototype updates (ablation) | DSP with f-VAEGAN · CUB and SUN (GZSL) | H: 54.8 -> 67.4; 42.1 -> 48.1 | Improved |
| Concatenate evolved prototypes with visual features (ablation) | DSP with f-VAEGAN · CUB and SUN (GZSL) | H: 53.1 -> 67.4; 42.5 -> 48.1 | Improved |
| Remove semantic reconstruction loss (ablation) | DSP with f-VAEGAN · CUB and SUN (GZSL) | H: 67.4 -> 65.5; 48.1 -> 45.4 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FREE — FREE: Feature Refinement for Generalized Zero-Shot Learning (ICCV 2021) · better on 2 of 2 shared results
- HSVA — HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning (NeurIPS 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning (CVPR 2024 · similarity 0.92)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.90)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · similarity 0.89)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.89)
- Simple Semantic-Aided Few-Shot Learning (CVPR 2024 · similarity 0.88)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 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.
