Research map / Label-efficient and robust learning / Recognition and long-tail
To Label or Not to Label: PALM - A Predictive Model for Evaluating Sample Efficiency in Active Learning Models
Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi
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 pretrained SSL embeddings to Margin sampling | Margin sampling · CIFAR-10 | delta: 0.094 -> 0.535 | Improved |
| add pretrained SSL embeddings to Random sampling | Random sampling · CIFAR-100 | delta: 0.048 -> 0.318 | Improved |
| add pretrained SSL embeddings to Margin sampling | Margin sampling · CIFAR-100 | alpha: 10.643 -> 0.068 | Improved |
| use embeddings with Random sampling versus Entropy sampling without embeddings | Active learning · CIFAR-10 | delta: 0.066 -> 0.536 | Improved |
| fit PALM on about 1,000 labeled samples instead of full curve | PALM · CIFAR-10 | curve prediction: 1,000 samples (2% of the dataset) | Improved |
| fit PALM on about 5,000 labeled samples | PALM · CIFAR-100 | curve prediction: 5,000 samples (10% of the dataset) | Improved |
| use MoCov3 embeddings instead of BYOL/MoCov2+ | Active learning · ImageNet-200 | A_max and delta | Improved |
| use BYOL embeddings | Active learning · ImageNet subsets | delta | Hurt |
| enlarge the number of fit points for BYOL | PALM · ImageNet subsets | curve fit | Mixed |
Closest papers by meaning
- Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment (NeurIPS 2023 · similarity 0.88)
- Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost (ECCV 2020 · similarity 0.88)
- Towards Cost-Effective Learning: A Synergy of Semi-Supervised and Active Learning (CVPR 2025 · similarity 0.87)
- A Cross-Domain Benchmark for Active Learning (NeurIPS 2024 · similarity 0.87)
- Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees (AAAI 2024 · similarity 0.87)
- Instance-wise Supervision-level Optimization in Active Learning (CVPR 2025 · 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.
