Research map / Label-efficient and robust learning / Recognition and long-tail
Active Learning for Convolutional Neural Networks: A Core-Set Approach
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 core-set selection with k-Center instead of the compared active-learning baselines | CNN active learning · CIFAR-10, CIFAR-100, and SVHN | classification accuracy | Helped |
| Use core-set selection with k-Center instead of the compared baselines | Weakly supervised CNN active learning · CIFAR-10, CIFAR-100, and SVHN | classification accuracy | Helped |
| Use the greedy 2-OPT k-Center solution instead of the MIP-based optimal solution (ablation) | Core-set active learning · CIFAR-100 | classification accuracy | Hurt |
| Use weakly supervised learning with Ladder networks, providing a better feature space | Core-set active learning · CIFAR-10, CIFAR-100, and SVHN | classification accuracy | Helped |
| Use empirical uncertainty sampling rather than random sampling | CNN active learning · CIFAR and SVHN | classification accuracy | Hurt |
| Use k-Medoids clustering to select query points | CNN active learning · CIFAR and SVHN | classification accuracy | Hurt |
| Use BMDR rather than greedy uncertainty-based methods | CNN active learning · CIFAR and SVHN | classification accuracy | Mixed |
Closest papers by meaning
- Active Convolution: Learning the Shape of Convolution for Image Classification (CVPR 2017 · similarity 0.91)
- Active Learning Through a Covering Lens (NeurIPS 2022 · similarity 0.89)
- Active Learning by Feature Mixing (CVPR 2022 · similarity 0.87)
- Sequential Graph Convolutional Network for Active Learning (CVPR 2021 · similarity 0.87)
- Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees (AAAI 2024 · similarity 0.86)
- Inconsistency-Based Data-Centric Active Open-Set Annotation (AAAI 2024 · similarity 0.85)
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.