Research map / Architectures and efficiency / CNN design
Memory Matching Networks for One-Shot Image Recognition
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 |
|---|---|---|---|
| Use mixed C-way k-shot training instead of training without the mixed strategy (ablation) | MM-Net · miniImageNet, 5-way 1-shot | accuracy: 52.74±0.45 -> 53.37 ± 0.48 | Helped |
| Use mixed C-way k-shot training instead of training without the mixed strategy (ablation) | MM-Net · miniImageNet, 5-way 5-shot | accuracy: 65.82± 0.37 -> 66.97 ± 0.35 | Helped |
| Vary both way count and shot count during training rather than vary shot count alone (ablation) | MM-Net · miniImageNet, 5-way 1-shot | accuracy: 52.83 -> 53.37 | Helped |
| Vary both way count and shot count during training rather than vary shot count alone (ablation) | MM-Net · miniImageNet, 5-way 5-shot | accuracy: 66.71 -> 66.97 | Helped |
| Use mixed k-shot training rather than fixed-shot training (ablation) | MM-Net · miniImageNet, 5-way k-shot | accuracy | Helped |
| Increase bi-LSTM hidden-state size across the tested choices (ablation) | MM-Net contextual learner · miniImageNet, 5-way 1-shot and 5-shot | accuracy: within 0.013 | No clear effect |
| Use MM-Net rather than MN | one-shot image recognition · Omniglot, 5-way 1-shot | accuracy: 98.1 -> 99.28 ± 0.08 | Helped |
| Use MM-Net rather than MN | one-shot image recognition · miniImageNet, 5-way 1-shot | accuracy: 43.40 ± 0.78 -> 53.37 ± 0.48 | Helped |
Closest papers by meaning
- Matching Networks for One Shot Learning (NeurIPS 2016 · similarity 0.90)
- Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models (CVPR 2024 · similarity 0.87)
- Multiscale Low-Frequency Memory Network for Improved Feature Extraction in Convolutional Neural Networks (AAAI 2024 · similarity 0.86)
- Self-Prompt Mechanism for Few-Shot Image Recognition (AAAI 2024 · similarity 0.86)
- PICNN: A Pathway towards Interpretable Convolutional Neural Networks (AAAI 2024 · similarity 0.86)
- Towards flexible perception with visual memory (ICML 2025 · 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.