Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification
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 |
|---|---|---|---|
| Jointly use web images for test categories and labeled auxiliary categories | Fine-grained classification · CUB | accuracy: 72.21 -> 76.47 | Helped |
| Jointly use web images for test categories and labeled auxiliary categories | Fine-grained classification · SUN | accuracy: 78.50 -> 84.50 | Helped |
| Jointly use web images for test categories and labeled auxiliary categories | Fine-grained classification · Dogs | accuracy: 81.90 -> 85.16 | Helped |
| Jointly use web images and auxiliary-category transfer | Fine-grained classification · CUB generalized setting | accuracy: 57.60 -> 59.60 | Helped |
| Jointly use web images and auxiliary-category transfer | Fine-grained classification · SUN generalized setting | accuracy: 35.11 -> 36.00 | Helped |
| Jointly use web images and auxiliary-category transfer | Fine-grained classification · Dogs generalized setting | accuracy: 55.13 -> 65.89 | Helped |
| Add knowledge transfer from labeled auxiliary categories (ablation) | Ours WSL · CUB | accuracy: 69.42 -> 76.47 | Helped |
| Add knowledge transfer from labeled auxiliary categories (ablation) | Ours WSL · SUN | accuracy: 65.50 -> 84.50 | Helped |
| Add knowledge transfer from labeled auxiliary categories (ablation) | Ours WSL · Dogs | accuracy: 80.43 -> 85.16 | Helped |
| Add web-data regularizers (ablation) | Ours ZSL · CUB | accuracy: 47.94 -> 76.47 | Helped |
| Add web-data regularizers (ablation) | Ours ZSL · SUN | accuracy: 71.50 -> 84.50 | Helped |
| Add web-data regularizers (ablation) | Ours ZSL · Dogs | accuracy: 47.70 -> 85.16 | Helped |
Closest papers by meaning
- Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs (NeurIPS 2025 · similarity 0.88)
- Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions (CVPR 2024 · similarity 0.88)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.86)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.86)
- Fine-grained Classes and How to Find Them (ICML 2024 · similarity 0.86)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.86)
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.