Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Active Learning With Temporal Output Discrepancy
Siyu Huang, Tianyang Wang, Haoyi Xiong, Jun Huan, Dejing Dou
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 TOD semi-supervised task learning (ablation) | Base · Cifar10 (40% labels) | accuracy: 91.8 -> 92.2 (+0.4) | Improved |
| add TOD active data selection (ablation) | Base · Cifar10 (40% labels) | accuracy: 91.8 -> 94.2 (+2.4) | Improved |
| add both semi-supervised learning and active selection (ablation) | Base · Cifar10 (40% labels) | accuracy: 91.8 -> 94.5 (+2.7) | Improved |
| add TOD semi-supervised task learning (ablation) | Base · Cifar100 (40% labels) | accuracy: 62.3 -> 66.1 (+3.8) | Improved |
| add TOD active data selection (ablation) | Base · Cifar100 (40% labels) | accuracy: 62.3 -> 67.3 (+5.0) | Improved |
| add both semi-supervised learning and active selection (ablation) | Base · Cifar100 (40% labels) | accuracy: 62.3 -> 68.5 (+6.2) | Improved |
| add TOD-based unsupervised loss (ablation) | task model · Cityscapes (40% labels, 19 classes) | mIoU: 54.7 -> 58.9 | Improved |
| use CyclicOD (last-cycle model baseline) vs EMAOD for sampling (ablation) | TOD sampling · Cifar-100 | accuracy | Mixed |
| use TOD-based sampling instead of random or LL4AL sampling (ablation) | active learning · Cifar-10 and Cifar-100 | accuracy | Improved |
| use EMA baseline model (EMAOD) for the unsupervised loss instead of CyclicOD (ablation) | TOD unsupervised loss · Cifar-10 and Cifar-100 | accuracy | Improved |
| replace learned loss predictor (LL4AL) with COD for sampling | active sampling · Cifar-10 | sampling time (s): 7.7 -> 7.2 | Improved |
Closest papers by meaning
- Boosting Active Learning via Improving Test Performance (AAAI 2022 · similarity 0.89)
- Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost (ECCV 2020 · similarity 0.88)
- STARS: Spatial-Temporal Active Re-sampling for Label-Efficient Learning from Noisy Annotations (AAAI 2023 · similarity 0.87)
- A Cross-Domain Benchmark for Active Learning (NeurIPS 2024 · similarity 0.86)
- Towards Cost-Effective Learning: A Synergy of Semi-Supervised and Active Learning (CVPR 2025 · similarity 0.86)
- Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation (ICML 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.
