Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Towards Task Sampler Learning for Meta-Learning
Jingyao Wang, Wenwen Qiang, Xingzhe Su, Changwen Zheng, Fuchun Sun, Hui Xiong
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 |
|---|---|---|---|
| use ASr adaptive sampler instead of uniform sampling | MAML · miniImagenet | accuracy: 48.51 -> 51.91 | Improved |
| use ASr instead of uniform sampling | SCNAP · miniImagenet | accuracy: 70.61 -> 73.52 | Improved |
| use ASr instead of uniform sampling | ProtoNet · miniImagenet | accuracy: 49.29 -> 49.37 | No clear effect |
| use low-diversity NDT sampler instead of uniform | MAML · miniImagenet | accuracy: 48.51 -> 35.47 | Hurt |
| use high-diversity OHTM sampler instead of uniform | MAML · miniImagenet | accuracy: 48.51 -> 47.15 | Hurt |
| use adaptive GCP sampler instead of uniform | ProtoNet · miniImagenet | accuracy: 49.29 -> 48.32 | Hurt |
| use ASr instead of uniform sampling | MAML · Sinusoid regression | MSE: 0.94 -> 0.69 | Improved |
| use ASr instead of uniform sampling | MAML · Harmonic regression | MSE: 0.99 -> 0.95 | Improved |
| use ASr instead of uniform sampling | MAML · Pose prediction (10-shot) | MSE: 3.121 -> 2.455 | Improved |
| use ASr instead of uniform sampling | MetaRCNN · Object detection (5-way 1-shot) | nAP: 19.03 -> 21.38 | Improved |
| use ASr instead of uniform sampling | BAM · Semantic segmentation (1-shot) | mIoU: 64.41 -> 65.82 | Improved |
| use ASr instead of uniform sampling | MAML · Drug activity prediction (Group 1) | mean R2: 0.372 -> 0.405 | Improved |
Closest papers by meaning
- Meta-learning with an Adaptive Task Scheduler (NeurIPS 2021 · similarity 0.91)
- Adaptive Task Sampling for Meta-Learning (ECCV 2020 · similarity 0.90)
- The Effect of Diversity in Meta-Learning (AAAI 2023 · similarity 0.90)
- Improving Generalization in Meta-learning via Task Augmentation (ICML 2021 · similarity 0.90)
- Meta-Learning with Fewer Tasks through Task Interpolation (ICLR 2022 · similarity 0.89)
- Advances and Challenges in Meta-Learning: A Technical Review (TPAMI 2024 · similarity 0.89)
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.
