Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Adaptive Task Sampling for Meta-Learning
Chenghao Liu, Zhihao Wang, Doyen Sahoo, Yuan Fang Kun Zhang, Steven C.H. Hoi
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 gcp-sampling | PN (ResNet-12) · miniImageNet 5-way 1-shot | accuracy: 59.25 -> 61.09 | Improved |
| add gcp-sampling | MetaOptNet-SVM (ResNet-12) · miniImageNet 5-way 1-shot | accuracy: 62.64 -> 64.01 | Improved |
| add gcp-sampling | PN (ResNet-12) · CIFAR-FS 5-way 5-shot | accuracy: 84.2 -> 84.5 | Improved |
| add gcp-sampling | PN (ResNet-12) · tieredImageNet 5-way 1-shot | accuracy: 61.74 -> 62.80 | Improved |
| add gcp-sampling | PN (Conv-4) · miniImageNet 5-way 1-shot (Conv-4) | accuracy: 44.15 -> 47.13 | Improved |
| add gcp-sampling | MAML++ (Conv-4) · CIFAR-FS 5-way 5-shot (Conv-4) | accuracy: 73.86 -> 73.98 | No clear effect |
| add gcp-sampling | Matching Network (Conv-4) · CIFAR-FS 5-way 1-shot (Conv-4) | accuracy: 53.14 -> 54.72 | Improved |
| use gcp-sampling with hard class pairs instead of random sampling (ablation) | MAML++ (Conv-4) · miniImageNet 5-way 1-shot (Conv-4) | accuracy: 50.60 -> 52.34 | Improved |
| use class-pair (gcp) sampling instead of class-based c-sampling (ablation) | MAML++ (Conv-4) · CIFAR-FS 5-way 1-shot (Conv-4) | accuracy: 58.61 -> 60.14 | Improved |
| use hard instead of easy class pairs in gcp-sampling (ablation) | MAML++ (Conv-4) · miniImageNet 5-way 1-shot (Conv-4) | accuracy: 50.88 -> 52.34 | Improved |
| use hard instead of uncertain class pairs in gcp-sampling (ablation) | MAML++ (Conv-4) · miniImageNet 5-way 1-shot (Conv-4) | accuracy: 51.73 -> 52.34 | Improved |
| use hard class pairs in gcp-sampling (ablation) | MAML++ (Conv-4) · CIFAR-FS 5-way 5-shot (Conv-4) | accuracy: 73.36 -> 74.58 | Improved |
Closest papers by meaning
- Meta-Learning without Memorization (ICLR 2020 · similarity 0.92)
- Task Agnostic Meta-Learning for Few-Shot Learning (CVPR 2019 · similarity 0.91)
- Improving Few-Shot Learning through Multi-task Representation Learning Theory (ECCV 2022 · similarity 0.91)
- Towards Task Sampler Learning for Meta-Learning (IJCV 2024 · similarity 0.90)
- Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy (ICCV 2025 · similarity 0.90)
- Meta-Learning with Fewer Tasks through Task Interpolation (ICLR 2022 · 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.
