Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning
Yinbo Chen, Zhuang Liu, Huijuan Xu, Trevor Darrell, Xiaolong Wang
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 meta-learning stage over converged Classifier-Baseline | Classifier-Baseline · miniImageNet 5-way 1-shot | accuracy (%): 58.91 -> 63.17 | Improved |
| add meta-learning stage over converged Classifier-Baseline | Classifier-Baseline · tieredImageNet 5-way 5-shot | accuracy (%): 83.74 -> 83.74 | No clear effect |
| add meta-learning stage over converged Classifier-Baseline | Classifier-Baseline (ResNet-50) · ImageNet-800 1-shot | accuracy (%): 86.07 -> 89.70 | Improved |
| add meta-learning stage over converged Classifier-Baseline | Classifier-Baseline (ResNet-50) · ImageNet-800 5-shot | accuracy (%): 96.14 -> 96.14 | No clear effect |
| add whole-classification training stage before meta-learning (ablation) | Meta-Baseline · miniImageNet 1-shot novel class generalization | accuracy (%): 58.54 -> 63.33 | Improved |
| add whole-classification training stage before meta-learning (ablation) | Meta-Baseline · miniImageNet 5-shot novel class generalization | accuracy (%): 74.95 -> 80.02 | Improved |
| add whole-classification training stage before meta-learning (ablation) | Meta-Baseline · miniImageNet 1-shot base class generalization | accuracy (%): 86.74 -> 86.42 | Hurt |
| use cosine instead of squared Euclidean distance (ablation) | Meta-Baseline · miniImageNet 5-way 1-shot | accuracy (%): 60.19 -> 63.33 | Improved |
| use cosine instead of squared Euclidean nearest-centroid at test time (ablation) | Classifier-Baseline · miniImageNet 5-way 1-shot | accuracy (%): 56.29 -> 60.58 | Improved |
| shuffle classes so base and novel classes are closer (mini subset) (ablation) | Meta-Baseline gain over Classifier-Baseline · tieredImageNet 1-shot | accuracy (%): +1.53 -> +4.24 | Improved |
| shuffle classes so base and novel classes are closer (full) (ablation) | Meta-Baseline gain over Classifier-Baseline · tieredImageNet 1-shot | accuracy (%): +0.76 -> +2.81 | Improved |
| train classifier with cosine classifier instead of linear (ablation) | Classifier-Baseline · miniImageNet 5-way 1-shot | accuracy (%): 60.58 -> 61.93 | Improved |
Later papers that compared with this method
11 later accepted papers report Meta-baseline as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.
- Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI (AAAI 2024 · better on 2 of 2 shared results)
- Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning (NeurIPS 2024 · better on 2 of 2 shared results)
- DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation (NeurIPS 2023 · better on 4 of 4 shared results)
- ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion (NeurIPS 2023 · better on 2 of 2 shared results)
- Prototype Completion for Few-Shot Learning (TPAMI 2023 · better on 2 of 2 shared results)
- Robust Meta-Representation Learning via Global Label Inference and Classification (TPAMI 2023 · better on 1 of 1 shared result)
- Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition (ECCV 2022 · better on 6 of 6 shared results)
- Generating Representative Samples for Few-Shot Classification (CVPR 2022 · better on 4 of 4 shared results)
3 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (ICLR 2020 · similarity 0.93)
- Rethinking Few-shot Image Classification: A Good Embedding is All You Need? (ECCV 2020 · similarity 0.93)
- Few-Shot Learning With a Strong Teacher (TPAMI 2022 · similarity 0.93)
- A Theoretical Analysis of the Number of Shots in Few-Shot Learning (ICLR 2020 · similarity 0.92)
- Meta-Learning for Semi-Supervised Few-Shot Classification (ICLR 2018 · similarity 0.92)
- The Role of Global Labels in Few-Shot Classification and How to Infer Them (NeurIPS 2021 · similarity 0.92)
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.
