Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
CLEAR: Cumulative LEARning for One-Shot One-Class 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 CLEAR instead of One-Class SVM | one-shot one-class recognition · Caltech-256 | MAP: 0.061 -> 0.364 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · Caltech-256 | F1: 0.011 -> 0.176 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · CUB-200-2011 | MAP: 0.051 -> 0.068 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · CUB-200-2011 | F1: 0.01 -> 0.037 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · Flowers 102 | MAP: 0.068 -> 0.193 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · Flowers 102 | F1: 0.016 -> 0.087 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · MIT Indoor 67 | MAP: 0.025 -> 0.209 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · MIT Indoor 67 | F1: 0.003 -> 0.111 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · SUN attributes | MAP: 0.009 -> 0.081 | Helped |
| Use CLEAR instead of One-Class SVM | one-shot one-class recognition · SUN attributes | F1: 0.001 -> 0.041 | Helped |
| Replace the SVM decision-boundary classifier with logistic regression (ablation) | CLEAR · Caltech-256, CUB-200-2011, Flowers 102, MIT Indoor 67, SUN attributes | MAP and F1: Table 6 MAP: 0.31, 0.067, 0.092, 0.16, 0.058; F1: 0.17, 0.034, 0.045, 0.08, 0.025 | Mixed |
Closest papers by meaning
- One-Shot Image Classification by Learning to Restore Prototypes (AAAI 2020 · similarity 0.88)
- Multi-Attention Network for One Shot Learning (CVPR 2017 · similarity 0.87)
- Learning feed-forward one-shot learners (NeurIPS 2016 · similarity 0.86)
- ‘Less Than One’-Shot Learning: Learning N Classes From M < N Samples (AAAI 2021 · similarity 0.86)
- One-bit Supervision for Image Classification (NeurIPS 2020 · similarity 0.86)
- Adaptive Decision Boundary for Few-Shot Class-Incremental Learning (AAAI 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.