Research map / Label-efficient and robust learning / Semi-supervised learning
SaaS: Speed as a Supervisor for Semi-supervised Learning
Safa Cicek, Alhussein Fawzi, Stefano Soatto
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 SaaS pseudo-label inference on unlabeled data | ResNet18 supervised baseline · CIFAR-10 (4K labels) and SVHN (1K labels) | test error | Improved |
| project label posterior onto simplex with minimum probability 0.05 (label thresholding) (ablation) | SaaS Phase I · SVHN | unlabeled accuracy | Improved |
| increase number of unlabeled samples (ablation) | SaaS ResNet18 · SVHN | test accuracy | Improved |
| use batch size 25 instead of 100 (ablation) | SaaS Phase I · SVHN | unlabeled accuracy | Improved |
| add SGLD noise to weight updates with batch size 100 (ablation) | SaaS Phase I · SVHN | unlabeled accuracy | Improved |
| increase number of outer epochs for label posterior (ablation) | SaaS Phase I · CIFAR-10 | training loss decrease | Improved |
| remove data augmentation (ablation) | SaaS · CIFAR-10 and SVHN | accuracy | Improved |
Closest papers by meaning
- Realistic Evaluation of Deep Semi-Supervised Learning Algorithms (NeurIPS 2018 · similarity 0.85)
- Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning (ICML 2024 · similarity 0.83)
- Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection (NeurIPS 2024 · similarity 0.82)
- Revisiting Semi-Supervised Learning in the Era of Foundation Models (NeurIPS 2025 · similarity 0.82)
- Towards Cost-Effective Learning: A Synergy of Semi-Supervised and Active Learning (CVPR 2025 · similarity 0.82)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.82)
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.
