Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Learning to Compare: Relation Network for Few-Shot Learning
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 |
|---|---|---|---|
| Replace a fixed metric with an end-to-end learned deep nonlinear relation module | Relation Network · Omniglot 5-way 1-shot | accuracy: 99.0 -> 99.6 $\pm$ 0.2\% | Helped |
| Replace a fixed metric with an end-to-end learned deep nonlinear relation module | Relation Network · miniImageNet 5-way 1-shot | accuracy: 49.42 $ \pm $ 0.78\% -> 50.44 $\pm$ 0.82\% | Helped |
| Replace a fixed metric with an end-to-end learned deep nonlinear relation module | Relation Network · miniImageNet 5-way 5-shot | accuracy: 68.20 $\pm$ 0.66\% -> 65.32 $\pm$ 0.70\% | Hurt |
| Use a learned deep relation module rather than existing zero-shot alternatives | Relation Network · AwA 10-way 0-shot | hit@1 accuracy: 86.7 -> 84.5 | Hurt |
| Use a learned deep relation module rather than existing zero-shot alternatives | Relation Network · CUB 50-way 0-shot | hit@1 accuracy: 61.4 -> 62.0 | Helped |
| Use a learned deep relation module rather than existing zero-shot alternatives | Relation Network · AwA2 GBU GZSL | H: 45.1 -> 45.3 | Helped |
| Use a learned deep relation module rather than existing zero-shot alternatives | Relation Network · CUB GBU GZSL | H: 13.6 -> 47.0 | Helped |
Closest papers by meaning
- Rethinking Class Relations: Absolute-Relative Supervised and Unsupervised Few-Shot Learning (CVPR 2021 · similarity 0.90)
- Meta-Learning for Semi-Supervised Few-Shot Classification (ICLR 2018 · similarity 0.89)
- A Baseline for Few-Shot Image Classification (ICLR 2020 · similarity 0.88)
- Few-Shot Learning with Graph Neural Networks (ICLR 2018 · similarity 0.88)
- Matching Networks for One Shot Learning (NeurIPS 2016 · similarity 0.88)
- Simple Semantic-Aided Few-Shot Learning (CVPR 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.