Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Prototype Rectification for Few-Shot Learning
Jinlu Liu, Liang Song, Yongqiang Qin
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 intra-class bias diminishing (ablation) | CSPN (WRN-28-10) · miniImageNet 1-shot | accuracy: 61.84 -> 69.81 | Improved |
| add intra-class bias diminishing (ablation) | CSPN (WRN-28-10) · tieredImageNet 1-shot | accuracy: 69.20 -> 78.12 | Improved |
| add intra-class bias diminishing (ablation) | CSPN (WRN-28-10) · miniImageNet 5-shot | accuracy: 78.64 -> 81.58 | Improved |
| add intra-class bias diminishing (ablation) | CSPN (WRN-28-10) · tieredImageNet 5-shot | accuracy: 84.31 -> 86.67 | Improved |
| add cross-class bias diminishing (ablation) | CSPN (WRN-28-10) · tieredImageNet 1-shot | accuracy: 69.20 -> 70.84 | Improved |
| add cross-class bias diminishing (ablation) | CSPN (WRN-28-10) · miniImageNet 1-shot | accuracy: 61.84 -> 62.54 | Improved |
| add cross-class bias diminishing (ablation) | CSPN (WRN-28-10) · miniImageNet 5-shot | accuracy: 78.64 -> 79.32 | Improved |
| add cross-class bias diminishing on top of intra-class (ablation) | BD_i-CSPN · tieredImageNet 1-shot | accuracy: 78.12 -> 78.74 | Improved |
| add both bias diminishing modules (ablation) | CSPN (ConvNet-128) · miniImageNet 1-shot | accuracy: 55.62 -> 61.74 | Improved |
| add both bias diminishing modules (ablation) | CSPN (ResNet-12) · miniImageNet 5-shot | accuracy: 76.26 -> 79.23 | Improved |
| use BD-CSPN instead of Transductive Fine-Tuning | WRN-28-10 · miniImageNet 1-shot | accuracy: 65.73 -> 70.31 | Improved |
| use BD-CSPN instead of Transductive Fine-Tuning | ResNet-12 · miniImageNet 5-shot | accuracy: 74.53 -> 79.23 | Improved |
Closest papers by meaning
- Prototypical Networks for Few-shot Learning (NeurIPS 2017 · similarity 0.90)
- Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement (CVPR 2023 · similarity 0.90)
- A Closer Look at Prototype Classifier for Few-shot Image Classification (NeurIPS 2022 · similarity 0.89)
- Provably Improving Generalization of Few-shot models with Synthetic Data (ICML 2025 · similarity 0.89)
- Compositional Prototypical Networks for Few-Shot Classification (AAAI 2023 · similarity 0.88)
- Mind the Gap Between Prototypes and Images in Cross-domain Finetuning (NeurIPS 2024 · 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.
