Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Learning to Learn By Self-Critique
Antreas Antoniou, Amos J. Storkey
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 SCA using target-set predictions as critic input | MAML++ (Low-End) · Mini-ImageNet 1-shot | test accuracy: $51.41 \pm 0.20\%$ -> $\mathbf{55.38 \pm 0.39\%}$ | Improved |
| Add SCA using target-set predictions as critic input | MAML++ (Low-End) · Mini-ImageNet 5-shot | test accuracy: $69.25 \pm 0.25\%$ -> $70.42 \pm 1.25\%$ | No clear effect |
| Add SCA using target-set predictions as critic input | MAML++ (Low-End) · CUBS-200 1-shot | test accuracy: $55.62\pm1.57\%$ -> $57.92\pm 1.55\%$ | No clear effect |
| Add SCA using target-set predictions as critic input | MAML++ (Low-End) · CUBS-200 5-shot | test accuracy: $68.19\pm 0.86\%$ -> $\mathbf{69.96\pm 0.26}\%$ | Improved |
| Use the reproduced High-End MAML++ setup rather than the reported original setup | MAML++ (High-End) · Mini-ImageNet 1-shot | test accuracy: $58.37\pm 0.27\%$ -> $39.35 \pm 1.33\%$ | Hurt |
| Use the reproduced High-End MAML++ setup rather than the reported original setup | MAML++ (High-End) · CUBS-200 1-shot | test accuracy: $67.48\pm 1.44 \%$ -> $31.23 \pm 0.66\%$ | Hurt |
Closest papers by meaning
- Few-Shot Learning With a Strong Teacher (TPAMI 2022 · similarity 0.90)
- Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning (ICCV 2021 · similarity 0.89)
- Realistic evaluation of transductive few-shot learning (NeurIPS 2021 · similarity 0.89)
- Meta Navigator: Search for a Good Adaptation Policy for Few-Shot Learning (ICCV 2021 · similarity 0.89)
- Meta-Learning With Task-Adaptive Loss Function for Few-Shot Learning (ICCV 2021 · similarity 0.89)
- A Theoretical Analysis of the Number of Shots in Few-Shot Learning (ICLR 2020 · similarity 0.88)
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.
