Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
LibFewShot: A Comprehensive Library for Few-Shot Learning
Wenbin Li, Ziyi Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo
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 l2 normalization to RFS-simple test classifier (1-shot) (ablation) | RFS-simple · miniImageNet 5-way 1-shot | accuracy: 58.69 -> 61.61 | Improved |
| replace logistic regression test-tuning with l2-normalized 1-NN (5-shot) (ablation) | RFS-simple · miniImageNet 5-way 5-shot | accuracy: 78.80 -> 78.85 | Improved |
| replace logistic regression test-tuning with l2-normalized 1-NN (1-shot) (ablation) | RFS-simple · miniImageNet 5-way 1-shot | accuracy: 61.61 -> 60.64 | No clear effect |
| add episodic fine-tuning after pre-training with global labels (Two Stages) (ablation) | ProtoNet · miniImageNet 5-way 1-shot | accuracy: 6.46% improvement to 63.56% | Improved |
| add episodic fine-tuning after global pre-training (Two Stages) (ablation) | DN4 · miniImageNet 5-way 1-shot | accuracy: 4.34% improvement to 63.02% | Improved |
| add episodic fine-tuning after global pre-training (Two Stages) (ablation) | R2D2 · miniImageNet 5-way 1-shot | accuracy: 2.52% improvement to 62.04% | Improved |
| add cutmix strong augmentation (1-shot) (ablation) | ProtoNet, R2D2, RFS-simple · miniImageNet 5-way 1-shot | accuracy: +2.24%, +3.75%, +2.08% | Improved |
| add cutmix strong augmentation (5-shot) (ablation) | ProtoNet, R2D2, RFS-simple · miniImageNet 5-way 5-shot | accuracy: +3.69%, +5.71%, +2.2% | Improved |
| add mixup augmentation (5-shot) (ablation) | ProtoNet, R2D2, RFS-simple · miniImageNet 5-way 5-shot | accuracy: +2.57%, +2.54%, +0.41% | Improved |
| add self-distillation knowledge distillation (5-shot) (ablation) | ProtoNet, DN4, R2D2 · miniImageNet 5-way 5-shot | accuracy: +1.86%, +1.73%, +1.94% | Improved |
| add self-distillation knowledge distillation (1-shot) (ablation) | ProtoNet, DN4, R2D2 · miniImageNet 5-way 1-shot | accuracy: +2.18%, +0.65%, +2.06% | Improved |
| add rotation-prediction self-supervision (1-shot) (ablation) | ProtoNet, DN4, R2D2 · miniImageNet 5-way 1-shot | accuracy: +0.94%, +0.55%, +2.57% | Improved |
Closest papers by meaning
- A Closer Look at Few-shot Classification Again (ICML 2023 · similarity 0.92)
- Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference (CVPR 2022 · similarity 0.92)
- A Baseline for Few-Shot Image Classification (ICLR 2020 · similarity 0.92)
- Rethinking Few-shot Image Classification: A Good Embedding is All You Need? (ECCV 2020 · similarity 0.91)
- A Closer Look at Few-shot Classification (ICLR 2019 · similarity 0.91)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.90)
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.
